© 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. 71414
    Prev
    Next
    INDEX
    Explanations

    opening or continuing actions

    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
     which
    -1.52
     with
    -1.42
     made
    -1.20
     GREAT
    -1.16
    ("
    -1.14
     where
    -1.13
     Not
    -1.13
     späteren
    -1.13
     animosity
    -1.12
     &
    -1.09
    POSITIVE LOGITS
     it
    1.41
     黄色
    1.38
    ǯ
    1.33
    erapa
    1.30
     trochu
    1.28
     poffe
    1.27
    klaim
    1.27
     nastro
    1.25
     erhi
    1.23
     udah
    1.23
    Activations Density 0.067%

    No Known Activations