© 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. 14236
    Prev
    Next
    INDEX
    Explanations

    as many as

    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
     now
    -1.72
    Organisateur
    -1.38
    还有
    -1.28
     €)
    -1.28
     inol
    -1.27
    íns
    -1.27
    還有
    -1.25
    大幅
    -1.24
    这里
    -1.23
     ultimately
    -1.21
    POSITIVE LOGITS
     is
    1.60
    ,"
    1.41
     enough
    1.37
     a
    1.29
    lieving
    1.28
    available
    1.28
    以上に
    1.27
    -
    1.23
    了许多
    1.21
     --
    1.19
    Activations Density 0.064%

    No Known Activations