© 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. 76669
    Prev
    Next
    INDEX
    Explanations

    list of keywords

    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
    ો
    0.52
    Caching
    0.52
    apiKey
    0.51
    decimals
    0.49
    Benzoimidazol
    0.47
    HairColor
    0.47
    <unused2218>
    0.45
    ခံ
    0.45
    ducation
    0.45
    ያን
    0.45
    POSITIVE LOGITS
    LLY
    0.50
    𝓛
    0.45
    ED
    0.45
     muk
    0.45
     sighed
    0.45
     rusk
    0.44
    RIBUN
    0.43
     ज़िन्दगी
    0.42
     french
    0.42
    ڵی
    0.42
    Activations Density 0.001%

    No Known Activations