© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 73164
    Prev
    Next
    INDEX
    Explanations

    structured data

    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
    あー
    -1.05
    為に
    -1.05
     direkt
    -0.96
    ところに
    -0.93
     coût
    -0.88
    стма
    -0.88
    久し
    -0.86
     Kindern
    -0.85
    事が
    -0.84
     stellen
    -0.84
    POSITIVE LOGITS
    oczes
    1.11
    入り口
    0.84
     門
    0.84
     techo
    0.83
     as
    0.82
    theless
    0.79
    ثيق
    0.79
     utafiti
    0.79
     仲
    0.79
    gaven
    0.78
    Activations Density 0.263%

    No Known Activations