© 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. 97788
    Prev
    Next
    INDEX
    Explanations

    describing quantity or state

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

    belief in

    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
    캬
    0.51
    лын
    0.50
    Ку
    0.50
    翕
    0.49
    হাব
    0.48
    トラブル
    0.48
    感動
    0.47
    Описание
    0.46
    гада
    0.45
    Л
    0.45
    POSITIVE LOGITS
    t
    0.45
    uot
    0.43
     செய்
    0.42
     ومد
    0.41
     hoặc
    0.41
    seats
    0.41
     Hangzhou
    0.40
     ناخد
    0.40
    spacerItem
    0.40
     நிறை
    0.40
    Activations Density 0.001%

    No Known Activations