© 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. 34-GEMMASCOPE-RES-131K
    4. 55596
    Prev
    Next
    INDEX
    Explanations

    closing punctuation and symbols

    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_34/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
    りと
    -0.81
     několik
    -0.80
    eney
    -0.77
    !』
    -0.75
     öpp
    -0.75
    짜
    -0.72
    viamo
    -0.72
     リゾート
    -0.71
    ﹌
    -0.71
    </tbody>
    -0.70
    POSITIVE LOGITS
    endcsname
    0.79
    frost
    0.79
    offic
    0.77
    Chun
    0.75
    ෴
    0.75
     Maker
    0.75
    ıyı
    0.74
    tières
    0.74
    irst
    0.72
    Irrigation
    0.72
    Activations Density 0.022%

    No Known Activations