© 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. 107231
    Prev
    Next
    INDEX
    Explanations

    human camera, non smoking rooms, main scorers

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

    legally or discrimination

    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
     tecnologie
    0.50
    ᱤ
    0.50
     degraded
    0.49
     technologie
    0.48
     degradation
    0.48
     littérature
    0.48
     profesión
    0.47
     degrad
    0.47
     sì
    0.46
    েশের
    0.46
    POSITIVE LOGITS
    that
    0.50
     არ
    0.46
    aranteed
    0.45
    d
    0.43
    c
    0.43
    ard
    0.43
     দী
    0.42
     عند
    0.42
    antara
    0.42
    Allister
    0.41
    Activations Density 0.000%

    No Known Activations