© 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. 128832
    Prev
    Next
    INDEX
    Explanations

    Eli Lilly, Hogwarts, programming errors

    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
    ’
    -2.63
    ↵
    -2.55
    6
    -2.38
    *
    -2.34
    並不
    -2.25
     fragte
    -2.23
    -
    -2.20
    How
    -2.13
    髦
    -2.09
    \
    -2.08
    POSITIVE LOGITS
    哢
    3.02
    儅
    2.91
    इटम
    2.75
    蜮
    2.55
     namorados
    2.52
    犽
    2.47
    杙
    2.44
    鄚
    2.42
    縂
    2.41
    赁
    2.36
    Activations Density 0.001%

    No Known Activations