© 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. 58646
    Prev
    Next
    INDEX
    Explanations

    multiple languages

    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
    ing
    -3.03
    –
    -2.28
    搗
    -2.25
    為
    -2.20
     Placing
    -2.16
    咂
    -2.14
    ↵↵
    -2.11
    が悪い
    -2.05
     Acknowled
    -2.03
    くちゃ
    -2.02
    POSITIVE LOGITS
    ’
    3.34
    鲠
    3.27
    ે
    2.61
    는
    2.44
     οπο
    2.41
    ی
    2.33
    ){
    2.28
    idenav
    2.25
     práctica
    2.23
    ));
    2.22
    Activations Density 0.000%

    No Known Activations