© 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. 8253
    Prev
    Next
    INDEX
    Explanations

    exams and assessment

    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
    ם
    0.92
    of
    0.91
    in
    0.85
    w
    0.84
    ى
    0.84
    b
    0.83
    지
    0.82
    ون
    0.79
    at
    0.79
    ες
    0.75
    POSITIVE LOGITS
    س
    1.05
    4
    1.03
    8
    1.03
    6
    0.95
    7
    0.94
    5
    0.85
    _
    0.81
    с
    0.79
    :
    0.78
    3
    0.78
    Activations Density 0.001%

    No Known Activations