Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 13807
    Prev
    Next
    INDEX
    Explanations

    definitions and experiments

    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
     slander
    0.47
    螌
    0.47
    ʝ
    0.46
     necesito
    0.46
    ayette
    0.45
    ſſ
    0.45
    uterte
    0.45
    ട
    0.45
     ಕೂಡ
    0.45
    ലെസ്
    0.45
    POSITIVE LOGITS
     but
    0.54
     gardens
    0.52
     Gardens
    0.49
     B
    0.48
     Trials
    0.48
     Data
    0.46
     trials
    0.46
     Esports
    0.46
     Genetics
    0.46
     names
    0.45
    Activations Density 0.008%

    No Known Activations