© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44610
    Prev
    Next
    INDEX
    Explanations

    BT followed by punctuation or short words

    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
    柺
    -2.72
    béco
    -2.67
    𓇼
    -2.30
    क्टर
    -2.27
    說
    -2.22
     Which
    -2.22
    蘗
    -2.22
    鋮
    -2.17
    霙
    -2.17
    蜴
    -2.17
    POSITIVE LOGITS
    {
    3.75
    ]
    3.45
    ?
    3.28
    c
    2.89
    ).
    2.80
    =
    2.70
    ا
    2.67
    \"
    2.66
    ;
    2.59
     یک
    2.53
    Activations Density 0.004%

    No Known Activations