© 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. 19983
    Prev
    Next
    INDEX
    Explanations

    LaTeX document setup

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

    The neuron spotlights LaTeX syntax markers—especially optional‐argument brackets (“[” and “]”) and the command‐form star (“*”) used in starred variants of commands.

    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
    -
    -2.33
     gets
    -2.16
     believes
    -2.02
    Хотя
    -1.84
     chose
    -1.84
     boasts
    -1.83
     their
    -1.81
     invigor
    -1.72
     facilitates
    -1.71
     revital
    -1.69
    POSITIVE LOGITS
     startling
    2.13
     strikingly
    2.08
    嫆
    2.05
     amazingly
    2.00
     delightfully
    1.96
     podoba
    1.84
     astonishing
    1.83
    歺
    1.83
    釤
    1.83
     remarkably
    1.81
    Activations Density 0.005%

    No Known Activations