© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10650
    Prev
    Next
    INDEX
    Explanations

    place name

    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
    鹟
    -2.22
    妧
    -2.22
     القيام
    -2.06
    蚴
    -1.98
     wachten
    -1.95
    𓆏
    -1.93
     oficialmente
    -1.90
    tă
    -1.89
    loween
    -1.88
     toepassing
    -1.84
    POSITIVE LOGITS
    in
    2.11
    p
    2.09
    g
    2.08
    c
    1.91
    at
    1.90
    /
    1.87
    )
    1.84
     place
    1.84
     поскольку
    1.83
     where
    1.81
    Activations Density 0.022%

    No Known Activations