© 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. 10-GEMMASCOPE-RES-131K
    7. 335
    Prev
    Next
    INDEX
    Explanations

    interchangeable

    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
    気付
    -2.36
    躄
    -2.25
    导演
    -2.22
     untuk
    -2.19
    気づ
    -2.17
    出来ます
    -2.11
     die
    -2.08
    𔘓
    -2.03
     Fähigkeit
    -2.03
     unravel
    -2.03
    POSITIVE LOGITS
    '
    2.75
    ).
    2.58
    ungalow
    2.17
    σιμοποι
    2.06
    最后由
    2.06
    <
    2.02
    ".
    1.97
    hi
    1.94
    il
    1.92
    ],
    1.91
    Activations Density 0.003%

    No Known Activations