© 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. 32394
    Prev
    Next
    INDEX
    Explanations

    del Toro

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

    Allah and Islam

    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
    テール
    0.55
    パラメータ
    0.49
    serving
    0.47
    ground
    0.47
    態度
    0.47
    reactant
    0.46
    🇼
    0.45
    nek
    0.44
    cement
    0.44
    CISE
    0.44
    POSITIVE LOGITS
     erschien
    0.58
     in
    0.48
     cort
    0.46
     e
    0.46
    }:=
    0.44
     bericht
    0.44
    innen
    0.44
     éclair
    0.44
     eingerichtet
    0.44
     Effort
    0.43
    Activations Density 0.000%

    No Known Activations