© 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. 22-GEMMASCOPE-RES-131K
    7. 33084
    Prev
    Next
    INDEX
    Explanations

    ID followed by identifier

    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_22/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
    fest
    -0.96
    fourths
    -0.95
     Brand
    -0.94
    farma
    -0.93
    有不
    -0.91
    werks
    -0.87
    strator
    -0.86
    u
    -0.86
    og
    -0.86
     y
    -0.86
    POSITIVE LOGITS
    ⁈
    1.11
    effetto
    1.01
    uens
    1.01
    (ﾟ
    0.98
     тогда
    0.93
    گاب
    0.92
     averiguar
    0.91
    猻
    0.89
     entsprechende
    0.89
     entsprechenden
    0.89
    Activations Density 0.003%

    No Known Activations