© 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-65K
    7. 1816
    Prev
    Next
    INDEX
    Explanations

    code, lists, and calculations

    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_65k_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
    כל
    0.52
    }=$
    0.47
    รู
    0.47
    <unused338>
    0.46
    䟝
    0.46
    ባ
    0.46
    ኛውም
    0.45
    ทุก
    0.45
     הז
    0.45
    לי
    0.45
    POSITIVE LOGITS
     D
    0.64
     and
    0.61
     first
    0.61
     A
    0.57
     I
    0.56
     P
    0.55
     E
    0.55
     Research
    0.55
     two
    0.54
     Education
    0.53
    Activations Density 0.284%

    No Known Activations