© 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. 8643
    Prev
    Next
    INDEX
    Explanations

    chief followed by professional roles

    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
    т
    0.60
     gustó
    0.56
    ت
    0.55
     OPEC
    0.53
     aHUS
    0.52
     Kı
    0.50
    UpSync
    0.48
    ;|
    0.47
     мной
    0.47
     GPUs
    0.46
    POSITIVE LOGITS
     chief
    0.48
     disciplined
    0.46
     in
    0.46
    '
    0.45
     complaint
    0.45
     deprived
    0.44
     witness
    0.43
    Chief
    0.43
     prosecutor
    0.43
    ”
    0.43
    Activations Density 0.004%

    No Known Activations