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. 16-GEMMASCOPE-2-RES-262K
    4. 41783
    Prev
    Next
    INDEX
    Explanations

    synonym or antonym

    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_16_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
    s
    0.95
    in
    0.91
     on
    0.85
     Significance
    0.84
     Accreditation
    0.76
    a
    0.75
    er
    0.73
    _
    0.73
     introvert
    0.73
     nä
    0.72
    POSITIVE LOGITS
    یم
    0.92
    و
    0.84
    imizi
    0.83
    ای
    0.82
    ет
    0.81
    یر
    0.79
    م
    0.79
    ます
    0.77
    ين
    0.75
    ିକ
    0.75
    Activations Density 0.005%

    No Known Activations