© 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. 71998
    Prev
    Next
    INDEX
    Explanations

    teaching, countries, opens, poster, tulip

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

    text home to 741741

    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
    witch
    0.48
    or
    0.48
    is
    0.46
     并
    0.46
    aling
    0.45
     Devils
    0.45
    gets
    0.45
     Front
    0.44
    are
    0.43
    하다
    0.43
    POSITIVE LOGITS
    К
    0.68
     budynku
    0.60
    Ин
    0.57
     неравен
    0.55
    У
    0.54
    Ш
    0.52
    Щ
    0.52
    モデル
    0.51
    Modification
    0.50
    ขอ
    0.50
    Activations Density 0.000%

    No Known Activations