© 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. 16962
    Prev
    Next
    INDEX
    Explanations

    player has, danger and, snow white

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

    role playing, consent, harm

    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
     trouver
    0.41
     swoim
    0.40
    แนว
    0.38
     phiên
    0.38
     和
    0.38
    和社会
    0.38
     thrilling
    0.38
     mott
    0.38
     leden
    0.38
     Streaming
    0.37
    POSITIVE LOGITS
    because
    0.50
    which
    0.49
     ambayo
    0.48
    bs
    0.48
    avoid
    0.44
    vì
    0.43
    č
    0.43
    mn
    0.42
    introduction
    0.42
    ފ
    0.42
    Activations Density 0.000%

    No Known Activations