© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39115
    Prev
    Next
    INDEX
    Explanations

    restaurant contexts

    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
    潆
    -3.00
    灃
    -2.66
    1
    -2.19
    4
    -2.17
     drenched
    -2.17
    rakech
    -2.16
    ейчас
    -2.14
    ᷆
    -2.13
    geſ
    -2.13
    olução
    -2.13
    POSITIVE LOGITS
     is
    2.95
    .
    2.58
    ?」
    2.13
    ↵
    1.98
    🚗
    1.95
    1.95
    ’’
    1.91
     chocolat
    1.91
     preis
    1.91
    .《
    1.89
    Activations Density 0.009%

    No Known Activations