© 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. 84065
    Prev
    Next
    INDEX
    Explanations

    Page -->

    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
     or
    -1.34
     atteint
    -1.32
    鹪
    -1.30
    就可以了
    -1.25
     noiembrie
    -1.23
     mogelijkheden
    -1.23
     giras
    -1.22
    蟊
    -1.21
    lusconi
    -1.21
    ondern
    -1.21
    POSITIVE LOGITS
     others
    1.23
    人
    1.20
    codiles
    1.17
    Likelihood
    1.16
    cznej
    1.16
     they
    1.16
     also
    1.13
    荔
    1.13
    맺
    1.13
     волосся
    1.12
    Activations Density 0.034%

    No Known Activations