© 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. 50573
    Prev
    Next
    INDEX
    Explanations

    SSL routines

    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
     foodie
    0.48
    "
    0.47
     Sü
    0.46
     sweets
    0.44
     miso
    0.43
     سود
    0.43
     falt
    0.43
     hedon
    0.42
     uptime
    0.42
    スイーツ
    0.42
    POSITIVE LOGITS
    ार्म
    0.47
    ocyst
    0.46
    ar
    0.46
    ık
    0.46
     Builders
    0.45
    ṛ
    0.45
    ulsions
    0.43
    ığı
    0.43
     Pistol
    0.43
     материал
    0.43
    Activations Density 0.002%

    No Known Activations