© 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. 42069
    Prev
    Next
    INDEX
    Explanations

    beyond

    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
     Δ
    0.40
     Aussage
    0.39
    liferation
    0.38
     increase
    0.37
    urface
    0.36
     increases
    0.36
    ̬
    0.36
    oshape
    0.36
    ிகளின்
    0.36
     aumentar
    0.35
    POSITIVE LOGITS
     столь
    0.44
    那里
    0.41
     ذلك
    0.39
    ᱤ
    0.38
     semuanya
    0.37
    ãs
    0.37
    CodeDict
    0.37
    そこ
    0.36
    ავ
    0.35
     teljesen
    0.35
    Activations Density 0.084%

    No Known Activations