© 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. 750
    Prev
    Next
    INDEX
    Explanations

    parser =

    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
    i
    1.64
    are
    1.30
    t
    1.26
    y
    1.15
    は
    1.13
    aren
    1.11
    res
    1.07
    .
    1.07
    to
    1.02
    iem
    1.02
    POSITIVE LOGITS
    ल
    1.46
    л
    1.23
    ти
    1.23
    ל
    1.17
    ד
    1.15
    ות
    1.12
    ы
    1.07
    у
    1.02
    ת
    1.02
    이었
    0.98
    Activations Density 0.008%

    No Known Activations