© 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. 34-GEMMASCOPE-RES-131K
    7. 99820
    Prev
    Next
    INDEX
    Explanations

    job titles and roles

    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_34/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
     afbeelding
    -1.17
     gada
    -1.17
     hvilken
    -1.14
    ⿺
    -1.14
     telefoon
    -1.13
    niest
    -1.11
     sosis
    -1.09
     afbeeldingen
    -1.09
     dava
    -1.09
     brisa
    -1.07
    POSITIVE LOGITS
     at
    3.13
     |
    1.56
     -
    1.32
     @
    1.17
     иногда
    1.15
     //
    1.08
    --
    1.05
    —
    1.04
    ;
    1.04
    const
    1.01
    Activations Density 0.020%

    No Known Activations