© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 103058
    Prev
    Next
    INDEX
    Explanations

    version numbers

    np_acts-logits-general · gemini-2.5-flash-lite

    decimal points in version numbers or numerical identifiers.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     what
    -1.63
     jsou
    -1.51
    瞥
    -1.45
    ázs
    -1.43
    дости
    -1.40
    棪
    -1.39
     sonriendo
    -1.39
    [:]
    -1.37
    鍇
    -1.36
    拶
    -1.35
    POSITIVE LOGITS
    ↵↵
    1.34
     セットアップ
    1.33
    ]]);
    1.31
    ulary
    1.28
    িস
    1.26
     キャプ
    1.25
     小説
    1.23
     スケ
    1.21
    ┙
    1.20
    !");
    1.19
    Activations Density 0.078%

    No Known Activations