© 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. 233392
    Prev
    Next
    INDEX
    Explanations

    falling off, generation strategies, Virginia Car, Safe Neighborhood

    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
    iu
    0.50
    iw
    0.49
     Mass
    0.48
    ’
    0.48
     volcano
    0.47
     Bergamo
    0.46
     fluvial
    0.46
     Bon
    0.46
    -
    0.46
     Marcia
    0.45
    POSITIVE LOGITS
    वर्तमान
    0.53
    ballage
    0.53
     CURRENT
    0.52
    غ
    0.50
    ८
    0.50
    ﻹ
    0.49
    ३
    0.49
    प्लाई
    0.48
    ﺙ
    0.47
    부는
    0.47
    Activations Density 0.000%

    No Known Activations