© 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. 210
    Prev
    Next
    INDEX
    Explanations

    abstract nouns and states

    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
    पणे
    0.37
    ร
    0.37
    রন
    0.37
    ‘
    0.37
    in
    0.35
    nor
    0.35
    র
    0.34
    ᱷ
    0.34
    sa
    0.34
     شدن
    0.34
    POSITIVE LOGITS
    และความ
    0.52
     ความ
    0.50
     ensues
    0.47
    पूर्ण
    0.47
     abound
    0.46
    ຄວາມ
    0.43
     acuity
    0.43
     invariance
    0.42
     incontinence
    0.42
     prudence
    0.42
    Activations Density 0.048%

    No Known Activations