© 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-65K
    7. 303
    Prev
    Next
    INDEX
    Explanations

    emojis and punctuation

    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_65k_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
    0.65
    e
    0.54
    a
    0.54
    an
    0.53
    to
    0.53
    p
    0.49
    ด
    0.47
    Q
    0.46
    ’
    0.46
    am
    0.46
    POSITIVE LOGITS
    0.52
    .
    0.47
    ę
    0.41
    لي
    0.40
    过来
    0.37
    é
    0.37
    (
    0.36
    $('#
    0.36
     lidí
    0.36
    سي
    0.35
    Activations Density 0.388%

    No Known Activations