© 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. 102346
    Prev
    Next
    INDEX
    Explanations

    finding lists and next steps

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

    styles and descriptors

    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
    Ꮏ
    0.51
    ت
    0.48
     জায়গায়
    0.48
     świet
    0.47
     esté
    0.47
     créer
    0.47
    یا
    0.46
     Esto
    0.46
     canción
    0.46
    谊
    0.46
    POSITIVE LOGITS
     discouraged
    0.42
     distress
    0.42
     অভিনেত্রী
    0.40
     liabilities
    0.40
     актриса
    0.39
     постра
    0.39
     приве
    0.38
     movements
    0.38
     fatigue
    0.37
     говори
    0.37
    Activations Density 0.003%

    No Known Activations