© 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. 72628
    Prev
    Next
    INDEX
    Explanations

    outright lying, downright scared, frank hypercortisolism

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

    The neuron activates for the word "outright" and other adverbs or phrases expressing directness or immediacy.

    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
    {
    -3.19
    at
    -2.70
    }$
    -2.56
    on
    -2.50
     "
    -2.47
    in
    -2.22
     eminent
    -2.22
     {
    -2.11
    蔼
    -2.03
    鲞
    -2.03
    POSITIVE LOGITS
    蹌
    2.84
    錞
    2.72
    ｍ
    2.59
    锭
    2.53
    嘞
    2.52
    是你
    2.48
    ⢕
    2.48
     शुर
    2.47
    ományos
    2.42
    ly
    2.41
    Activations Density 0.000%

    No Known Activations