© 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. 186111
    Prev
    Next
    INDEX
    Explanations

    groups of people and places

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

    Jensen, Silent, War, Charging, magnitude, Potential

    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
     because
    0.54
     porque
    0.48
     elucidate
    0.48
     dement
    0.48
    今後の
    0.47
    ².
    0.46
     Elegant
    0.45
     Ã
    0.45
     menacing
    0.45
     dimensional
    0.43
    POSITIVE LOGITS
    ellers
    0.53
     书
    0.52
    emporary
    0.51
    hamilan
    0.49
    urow
    0.49
    osław
    0.49
     अस्थायी
    0.48
    骆
    0.48
    attoo
    0.48
    ʛ
    0.48
    Activations Density 0.000%

    No Known Activations