© 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. 16-GEMMASCOPE-2-RES-262K
    7. 555
    Prev
    Next
    INDEX
    Explanations

    goal setting

    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
    し
    1.02
    ۳
    0.98
    padă
    0.95
    ные
    0.95
     αλλά
    0.95
    重要
    0.93
    τη
    0.93
    ના
    0.93
    uv
    0.92
    tų
    0.91
    POSITIVE LOGITS
    0
    1.45
    า
    1.21
    UR
    1.17
    an
    1.10
    IN
    1.10
    ized
    1.09
     \
    1.08
    5
    1.06
    AT
    1.02
    OS
    1.00
    Activations Density 0.038%

    No Known Activations