© 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. 14197
    Prev
    Next
    INDEX
    Explanations

    foreign names and words

    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
    com
    0.39
    est
    0.36
     MSG
    0.35
     Dams
    0.35
     в
    0.34
    别的
    0.34
     a
    0.34
     Bots
    0.34
     Masai
    0.33
     DVR
    0.33
    POSITIVE LOGITS
    лябин
    0.45
     रॉबर्ट
    0.44
     francese
    0.43
    ጴ
    0.43
     duckys
    0.42
     हेनरी
    0.42
    靗
    0.40
     ആദ്യ
    0.40
     pertama
    0.40
     ponen
    0.40
    Activations Density 0.000%

    No Known Activations