© 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. 22-GEMMASCOPE-RES-131K
    7. 128728
    Prev
    Next
    INDEX
    Explanations

    code punctuation and symbols

    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_22/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
     this
    -1.45
     for
    -1.30
     that
    -1.24
    ;
    -1.23
     fjor
    -1.23
     such
    -1.15
    Shortly
    -1.12
     their
    -1.12
     tertawa
    -1.09
     a
    -1.09
    POSITIVE LOGITS
     nuevamente
    1.20
    了
    1.06
     novamente
    1.05
     pretože
    1.05
     tiered
    1.03
    ha
    1.02
    vrier
    1.01
     жк
    1.01
     kilka
    1.00
    深处
    1.00
    Activations Density 0.000%

    No Known Activations