© 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. 73661
    Prev
    Next
    INDEX
    Explanations

    Android UI setup methods

    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
    蕯
    -2.23
     mengucap
    -2.19
     from
    -2.16
    、「
    -2.16
    /////////////
    -2.14
    /////////
    -2.14
    If
    -2.11
     incorporating
    -2.09
    //////////////
    -2.06
     TECN
    -2.03
    POSITIVE LOGITS
     tremendous
    2.44
     .......
    2.38
     ferocious
    2.36
     hizo
    2.36
    ...
    2.36
    </i>
    2.25
     horrible
    2.25
     VERY
    2.20
    罴
    2.19
     BECAUSE
    2.16
    Activations Density 0.001%

    No Known Activations