© 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. 73804
    Prev
    Next
    INDEX
    Explanations

    hex masks and constants

    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
    ⏑
    -2.38
    啣
    -2.28
    ⚣
    -2.17
    蹰
    -2.17
    癭
    -2.11
    瀣
    -2.11
    hiva
    -2.11
     nuova
    -2.08
     himſelf
    -2.02
    |}{\
    -2.02
    POSITIVE LOGITS
    C
    2.25
    )
    2.25
    n
    2.22
    、
    2.14
    o
    2.08
    w
    2.06
    ally
    2.05
    !"
    2.05
    ,"
    2.02
    h
    1.98
    Activations Density 0.000%

    No Known Activations