© 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. 169887
    Prev
    Next
    INDEX
    Explanations

    live streaming

    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
     contin
    0.48
     mécanisme
    0.46
     പക്ഷേ
    0.45
    仕組み
    0.44
    醤
    0.43
     sapere
    0.43
     cambio
    0.41
     actively
    0.41
     uso
    0.40
     passo
    0.40
    POSITIVE LOGITS
    Attributes
    0.45
    특별시
    0.44
    𝙢
    0.44
    줘
    0.44
    Hilbert
    0.43
    Request
    0.42
    Header
    0.42
    tDBOutput
    0.42
    Decorative
    0.41
    uut
    0.41
    Activations Density 0.001%

    No Known Activations