© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-65K
    7. 390
    Prev
    Next
    INDEX
    Explanations

    dialogue attribution ends with quote

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_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
     형태
    0.95
     이벤트
    0.93
     제공
    0.91
     leftovers
    0.89
    侪
    0.87
     다른
    0.86
     사람들
    0.85
     스
    0.85
    <unused2124>
    0.84
     종류
    0.83
    POSITIVE LOGITS
     said
    0.93
    said
    0.86
     says
    0.85
    says
    0.78
     remark
    0.73
     lamented
    0.73
    .
    0.72
     explica
    0.69
     explains
    0.66
    expl
    0.65
    Activations Density 0.084%

    No Known Activations