© 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. 57227
    Prev
    Next
    INDEX
    Explanations

    over the course of

    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
    ക്ക്
    -0.86
     what
    -0.81
    ＝＝＝＝
    -0.78
     recently
    -0.74
     kürzlich
    -0.72
    Recently
    -0.71
     flé
    -0.71
     from
    -0.69
     前
    -0.68
     principale
    -0.68
    POSITIVE LOGITS
     pity
    1.42
    THA
    1.04
     Pity
    0.94
    hoots
    0.88
    ﯿ
    0.86
    zwei
    0.84
     Espagne
    0.84
    CompanyName
    0.82
    trat
    0.82
     Retrofit
    0.82
    Activations Density 0.000%

    No Known Activations