© 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. 40-GEMMASCOPE-2-RES-262K
    7. 223250
    Prev
    Next
    INDEX
    Explanations

    online content

    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_40_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
    싼
    0.43
     Paragu
    0.42
    Abu
    0.41
    든
    0.40
     ஆண்
    0.40
    很少
    0.40
    Metall
    0.39
    Buenos
    0.38
    ไ
    0.37
     ré
    0.37
    POSITIVE LOGITS
     remarked
    0.44
     remarks
    0.43
     remark
    0.40
     Remarks
    0.39
     internship
    0.39
     absorbing
    0.38
    leys
    0.37
     communique
    0.37
     layoff
    0.37
     topical
    0.37
    Activations Density 0.000%

    No Known Activations