© 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. 67384
    Prev
    Next
    INDEX
    Explanations

    numbers and decimals

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     аккура
    -1.79
     where
    -1.74
    ኵ
    -1.70
    سایت
    -1.66
    Jahre
    -1.63
     expérimentés
    -1.62
     bluza
    -1.61
     dagar
    -1.60
     ४
    -1.58
    剮
    -1.58
    POSITIVE LOGITS
     we
    1.84
     
    1.70
     For
    1.68
     also
    1.63
     We
    1.55
    кладки
    1.50
     Or
    1.44
    Также
    1.43
    ;
    1.38
    sweise
    1.34
    Activations Density 0.051%

    No Known Activations