© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 12823
    Prev
    Next
    INDEX
    Explanations

    Suggest a specific activity

    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
    ล
    0.35
    பட
    0.35
    }$=
    0.35
    Ф
    0.34
     lunghezza
    0.33
     הק
    0.33
     secund
    0.33
     ல
    0.32
     quadrato
    0.32
    über
    0.32
    POSITIVE LOGITS
     hospitality
    0.30
     outings
    0.29
     CEOs
    0.29
     affordable
    0.28
     nonprofits
    0.28
     opioids
    0.28
     oceans
    0.28
     offerings
    0.28
     restaurants
    0.27
     Resorts
    0.27
    Activations Density 0.208%

    No Known Activations