© 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. 34-GEMMASCOPE-RES-131K
    7. 30644
    Prev
    Next
    INDEX
    Explanations

    postcodes

    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_34/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
     then
    -1.09
     and
    -1.02
    nữ
    -0.91
    SCRIPTION
    -0.88
     превра
    -0.85
    婊
    -0.82
    nhà
    -0.82
     Automate
    -0.82
    isset
    -0.81
     situation
    -0.81
    POSITIVE LOGITS
     afbeelding
    1.13
    бр
    1.10
    AA
    1.05
     illustratie
    1.03
    érêt
    1.02
     configurações
    1.02
    ጄ
    0.96
    AAT
    0.96
    TT
    0.96
    étaires
    0.96
    Activations Density 0.006%

    No Known Activations