© 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. 111205
    Prev
    Next
    INDEX
    Explanations

    list items or categories

    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
    0.47
     numerator
    0.43
     `
    0.41
    TA
    0.41
     AS
    0.40
     sectors
    0.39
     L
    0.38
     p
    0.38
     literally
    0.37
     diodes
    0.37
    POSITIVE LOGITS
     Lastly
    0.57
     എന്നിവ
    0.55
    และการ
    0.54
     अन्य
    0.54
     ఇతర
    0.53
     innych
    0.52
     інших
    0.52
     기타
    0.52
     infine
    0.51
     इतर
    0.51
    Activations Density 0.103%

    No Known Activations