© 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. 15604
    Prev
    Next
    INDEX
    Explanations

    code and command syntax

    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
    ඵ
    0.42
    駈
    0.40
     DOCUMENTS
    0.40
     विभक्ति
    0.40
     Erkrank
    0.40
    
    0.39
     Krankheit
    0.39
     Veamos
    0.39
     enfermo
    0.38
    verbal
    0.38
    POSITIVE LOGITS
     interface
    0.41
     Acceler
    0.40
    监听
    0.40
     @
    0.39
     mop
    0.38
     biztos
    0.38
     pool
    0.38
     indicates
    0.38
     SQLite
    0.38
     ইউ
    0.37
    Activations Density 0.101%

    No Known Activations