© 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. 194127
    Prev
    Next
    INDEX
    Explanations

    separation of religion

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

    collection of

    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
    es
    0.63
    H
    0.57
     設定
    0.51
     Einstellungen
    0.50
    in
    0.50
    SAV
    0.50
    CG
    0.48
    increase
    0.48
    يمكن
    0.47
    ES
    0.47
    POSITIVE LOGITS
     filo
    0.49
    autoarima
    0.48
    鹕
    0.45
    യില
    0.44
     scopo
    0.44
     RSM
    0.44
     сна
    0.43
     ferme
    0.43
     ठाकरे
    0.42
    を受ける
    0.42
    Activations Density 0.000%

    No Known Activations