© 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. 62732
    Prev
    Next
    INDEX
    Explanations

    circles ripple, contact us

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

    how you learn

    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
    2
    0.63
    ی
    0.58
    3
    0.54
    4
    0.53
    ین
    0.51
    し
    0.51
    га
    0.49
    6
    0.48
    kins
    0.47
    치
    0.47
    POSITIVE LOGITS
     It
    0.54
     financieras
    0.54
     prolong
    0.53
     verifica
    0.53
     perdió
    0.49
     provides
    0.48
     figuras
    0.48
     verifies
    0.47
     laughs
    0.47
     probablement
    0.47
    Activations Density 0.000%

    No Known Activations