© 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. 139
    Prev
    Next
    INDEX
    Explanations

    basic instructions

    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
    NE
    0.59
    Х
    0.53
    (
    0.50
    [
    0.50
    <
    0.50
    Union
    0.49
    Р
    0.49
    I
    0.48
    READ
    0.48
    WATER
    0.48
    POSITIVE LOGITS
    ા
    0.49
    ggac
    0.48
    ée
    0.46
     пробле
    0.45
     गर्भावस्था
    0.45
    া
    0.45
    ה
    0.45
    dafx
    0.44
     дости
    0.44
    㬹
    0.44
    Activations Density 0.000%

    No Known Activations