Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 11790
    Prev
    Next
    INDEX
    Explanations

    text and images

    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
     niego
    0.36
     ĝi
    0.36
    ви
    0.34
    guardo
    0.33
     possibilité
    0.32
     njega
    0.32
    で
    0.32
     équipée
    0.31
     его
    0.31
     اسے
    0.31
    POSITIVE LOGITS
    :
    0.42
     a
    0.41
     berbagai
    0.37
     highly
    0.37
     an
    0.37
     tzv
    0.36
     non
    0.36
     more
    0.36
     various
    0.35
     olyan
    0.35
    Activations Density 0.124%

    No Known Activations