© 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. 73370
    Prev
    Next
    INDEX
    Explanations

    sapphire

    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
    鴆
    -2.64
    袮
    -2.39
    哢
    -2.39
     uſed
    -2.22
     in
    -2.16
     desee
    -2.14
    ᕱ
    -2.14
     habl
    -2.08
    ޙ
    -2.06
    侂
    -2.06
    POSITIVE LOGITS
    Also
    2.64
    In
    2.45
    (
    2.41
    Are
    2.36
    Although
    2.33
    According
    2.33
    e
    2.30
    ↵
    2.28
     ряда
    2.25
    お待ち
    2.22
    Activations Density 0.002%

    No Known Activations