© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 67511
    Prev
    Next
    INDEX
    Explanations

    like / unlike

    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
    مجموع
    -0.94
    ligheter
    -0.91
     població
    -0.85
    Suisse
    -0.84
     zprá
    -0.82
    Bety
    -0.82
    Ꮺ
    -0.82
    ƨ
    -0.81
    Где
    -0.80
    Anzeige
    -0.80
    POSITIVE LOGITS
     like
    2.02
     Like
    1.33
     unlike
    1.16
     LIKE
    1.15
     مانند
    1.11
    像
    1.09
     zoals
    1.06
     nagu
    1.02
    เหมือน
    0.98
    Like
    0.96
    Activations Density 0.074%

    No Known Activations