© 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. 10851
    Prev
    Next
    INDEX
    Explanations

    describing states or actions

    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
     similarly
    0.27
     също
    0.24
    同樣
    0.24
    ও
    0.24
     també
    0.24
    同様
    0.24
    ম
    0.24
     Pháp
    0.23
     također
    0.23
     ৪
    0.22
    POSITIVE LOGITS
    ษฐ
    0.25
    ühlen
    0.24
     vasodil
    0.23
    </blockquote>
    0.23
    EnterExpr
    0.22
     wag
    0.22
     unaffected
    0.22
    Daten
    0.22
     inappropri
    0.22
    igment
    0.22
    Activations Density 0.190%

    No Known Activations