© 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. 85153
    Prev
    Next
    INDEX
    Explanations

    Vikram, Vikrant, rotavirus, Optimove

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

    names beginning with "Vik" like "Vikram" or references to viruses like "rotavirus".

    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
    𞤢
    -3.14
    𞤤
    -3.02
    𖧵
    -2.97
    🫅
    -2.88
    谞
    -2.81
    䜣
    -2.78
    沨
    -2.70
    聼
    -2.61
    </em>
    -2.55
    नलोड
    -2.55
    POSITIVE LOGITS
    of
    3.31
    op
    2.61
    if
    2.56
    en
    2.56
    il
    2.55
    ஂ
    2.50
    哢
    2.45
    It
    2.42
    it
    2.31
    when
    2.31
    Activations Density 0.013%

    No Known Activations