© 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. 34-GEMMASCOPE-RES-131K
    7. 63140
    Prev
    Next
    INDEX
    Explanations

    force upon

    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
    átku
    -0.94
    déric
    -0.94
     kanssa
    -0.84
    />";
    -0.84
     liitty
    -0.83
    URLEncoder
    -0.82
     potrzeb
    -0.82
    chito
    -0.81
     dziecko
    -0.80
    mapStateToProps
    -0.80
    POSITIVE LOGITS
     on
    5.06
     upon
    2.75
     onto
    2.11
    บน
    2.05
     على
    1.97
     روی
    1.91
    upon
    1.86
     عليهم
    1.75
     asupra
    1.73
     trên
    1.70
    Activations Density 0.067%

    No Known Activations