© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66408
    Prev
    Next
    INDEX
    Explanations

    words beginning with actin

    np_acts-logits-general · gemini-2.5-flash-lite

    references to actin or actinic, which are proteins or molecules in cellular structures and medical conditions.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron strongly activates on occurrences of the word “actin” (especially in technical compound terms like actin‐filaments or actin‐depolymerizing).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    焄
    -3.05
     ſou
    -2.88
    哢
    -2.88
    
    -2.86
    ⸫
    -2.78
    壼
    -2.75
    ⩴
    -2.64
    豨
    -2.61
    潆
    -2.58
    饹
    -2.58
    POSITIVE LOGITS
     extrêmement
    2.53
     vorigen
    2.50
     Allgemeinen
    2.44
    I
    2.34
     Thirty
    2.25
     Gegensatz
    2.19
     Much
    2.17
    $
    2.14
    ついに
    2.08
     dunklen
    2.08
    Activations Density 0.005%

    No Known Activations