© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 189836
    Prev
    Next
    INDEX
    Explanations

    car features, files, or references

    np_acts-logits-general · gemini-2.5-flash-lite

    feature engineering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    up
    0.47
     Connection
    0.45
     Foundation
    0.44
    ats
    0.44
     Par
    0.43
     is
    0.43
     L
    0.43
    rare
    0.43
    ak
    0.42
    are
    0.42
    POSITIVE LOGITS
    )]);
    0.48
     speculate
    0.46
     चले
    0.44
     mishap
    0.44
     beden
    0.43
     eröffnet
    0.43
     bevor
    0.42
     shovel
    0.42
     leth
    0.42
     speculating
    0.42
    Activations Density 0.000%

    No Known Activations