© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 44383
    Prev
    Next
    INDEX
    Explanations

    explicit sexual content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tasas
    0.47
    TIL
    0.46
    一緒に
    0.46
    Finding
    0.45
    پ
    0.45
    Finalmente
    0.45
    Assets
    0.45
    Ꮋ
    0.44
    ক
    0.44
    𒆠
    0.44
    POSITIVE LOGITS
     inappropriate
    0.48
     rarely
    0.48
     unable
    0.47
    rock
    0.47
     Solaris
    0.46
     surveillance
    0.46
     refuse
    0.45
     denied
    0.45
     unrealistic
    0.45
     disregarded
    0.44
    Activations Density 0.002%

    No Known Activations