© 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. 15234
    Prev
    Next
    INDEX
    Explanations

    URLs and citations

    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
     and
    -1.77
     using
    -1.46
    ！(
    -1.45
     like
    -1.45
     so
    -1.41
    ～！
    -1.41
     deres
    -1.38
     ),
    -1.34
    %"),
    -1.34
    ativement
    -1.34
    POSITIVE LOGITS
    差不多
    1.77
    キレイ
    1.57
    5
    1.55
    3
    1.53
     Tecnología
    1.53
     poucos
    1.52
    4
    1.52
     nossos
    1.52
     decidedly
    1.52
     antigos
    1.51
    Activations Density 0.092%

    No Known Activations