© 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. 71255
    Prev
    Next
    INDEX
    Explanations

    precomputed list or tensor IDCGs

    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
     осе
    0.50
    播出
    0.46
     моло
    0.44
    幡
    0.43
     ప్రక
    0.42
    дови
    0.42
    衩
    0.42
    عت
    0.42
    簹
    0.41
    十五
    0.41
    POSITIVE LOGITS
     Luc
    0.46
     hotel
    0.46
     skillful
    0.45
     "
    0.45
     topological
    0.44
     Mies
    0.43
     exploiting
    0.43
    ↵
    0.42
     criticizing
    0.42
     kemarin
    0.42
    Activations Density 0.004%

    No Known Activations