© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 19837
    Prev
    Next
    INDEX
    Explanations

    as long as, as little as, as much as

    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_10/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
    禤
    -1.77
    }
    -1.74
    m
    -1.70
    鄚
    -1.67
    ふわ
    -1.67
     our
    -1.66
    !».
    -1.65
     グラビア
    -1.64
    autre
    -1.63
    Примеча
    -1.62
    POSITIVE LOGITS
     BorderSide
    1.91
    remadura
    1.89
    ExtendWith
    1.87
    )
    1.81
    Those
    1.73
    enderror
    1.71
    LEncoder
    1.67
    ',
    1.66
    vetrain
    1.64
    ).
    1.61
    Activations Density 0.014%

    No Known Activations