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. 41757
    Prev
    Next
    INDEX
    Explanations

    and beans or whatever

    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
     favors
    0.55
     $/
    0.50
     coul
    0.50
     datar
    0.49
     Associations
    0.49
     thrills
    0.46
     fouls
    0.46
     Ithaca
    0.45
     Coul
    0.45
     organelles
    0.44
    POSITIVE LOGITS
    ropolis
    0.46
    ECUT
    0.44
    主流
    0.42
    ARIOS
    0.40
    一手
    0.40
     রাধানাথ
    0.40
    城
    0.40
     caregiver
    0.40
    ARI
    0.39
     القدر
    0.39
    Activations Density 0.002%

    No Known Activations