© 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. 59724
    Prev
    Next
    INDEX
    Explanations

    from the, a field

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

    geometry or code

    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
     Parisian
    0.47
    ی
    0.47
     weary
    0.47
    вався
    0.47
    ꧂
    0.46
    wegen
    0.45
    water
    0.45
    ">—
    0.45
     was
    0.44
     Theatre
    0.44
    POSITIVE LOGITS
     proporción
    0.53
     quotidienne
    0.51
     giường
    0.49
     déficit
    0.48
     Например
    0.47
     стратегия
    0.46
    TrackAngle
    0.46
     справо
    0.46
     пирами
    0.44
     кла
    0.44
    Activations Density 0.000%

    No Known Activations