© 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. 18725
    Prev
    Next
    INDEX
    Explanations

    selection of

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

    refusal of explicit or objectionable scenes

    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
     annen
    0.45
     andere
    0.44
     primul
    0.44
     modello
    0.42
    н
    0.42
     eerste
    0.42
     innych
    0.41
     estándares
    0.41
     otros
    0.41
     Déf
    0.40
    POSITIVE LOGITS
    データを
    0.46
    データの
    0.46
    automatically
    0.46
    自動
    0.46
    錯誤
    0.46
     illogical
    0.45
    偷
    0.45
    acing
    0.45
     careless
    0.45
    非法
    0.45
    Activations Density 0.000%

    No Known Activations