© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113535
    Prev
    Next
    INDEX
    Explanations

    actin and related biological terms

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

    The neuron detects the word "actin" and related biological/cellular terminology.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    9
    -3.36
     of
    -2.98
    3
    -2.92
     FROM
    -2.72
    6
    -2.66
    ist
    -2.66
     Provide
    -2.61
    1
    -2.55
     remarkably
    -2.52
    5
    -2.52
    POSITIVE LOGITS
    琑
    2.89
    ים
    2.84
    婓
    2.83
    婞
    2.70
    呯
    2.69
    reurs
    2.56
     idée
    2.48
     apparence
    2.45
    Ꮔ
    2.42
     ieee
    2.33
    Activations Density 0.002%

    No Known Activations