© 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. 175656
    Prev
    Next
    INDEX
    Explanations

    tiny micro

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

    writing erotic fiction

    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
    برای
    0.48
     tujuh
    0.45
     توصیه
    0.45
    CCl
    0.44
     ಏಕೆ
    0.43
    建议
    0.43
    愫
    0.42
     ஏன்
    0.42
     സ്ഥ
    0.42
    nestjs
    0.42
    POSITIVE LOGITS
     Henrietta
    0.49
     portland
    0.49
     capacit
    0.47
     wrinkled
    0.45
     yahoo
    0.45
     Riga
    0.45
     feria
    0.45
    𝙸
    0.45
    აზ
    0.45
     Oiseau
    0.44
    Activations Density 0.000%

    No Known Activations