© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 53273
    Prev
    Next
    INDEX
    Explanations

    plans in code

    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
    ГА
    0.46
    А
    0.46
    а
    0.45
    пта
    0.42
    ING
    0.42
    О
    0.42
     dimers
    0.40
    其他
    0.40
    К
    0.39
     이용하여
    0.38
    POSITIVE LOGITS
     Enhancement
    0.50
     After
    0.49
     aggior
    0.49
     Después
    0.48
     apparaissent
    0.48
     démarrage
    0.47
     écran
    0.47
     Within
    0.46
     Personalized
    0.46
     Fonction
    0.46
    Activations Density 0.005%

    No Known Activations