© 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. 39374
    Prev
    Next
    INDEX
    Explanations

    station opened or questions

    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
     осіб
    -1.11
    inā
    -1.06
    ține
    -1.05
    jante
    -1.05
     mitään
    -1.04
     membag
    -1.02
     autobuses
    -1.02
    StrictEqual
    -1.01
     just
    -0.99
    andaş
    -0.99
    POSITIVE LOGITS
    küche
    1.09
    сумка
    0.99
    pled
    0.97
    Komple
    0.96
    })\
    0.95
     ‘’
    0.95
    Kons
    0.94
    📠
    0.93
    tui
    0.92
     complimented
    0.92
    Activations Density 0.000%

    No Known Activations