© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 90377
    Prev
    Next
    INDEX
    Explanations

    names ending in 'a' or 'o'

    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
    ↵
    0.56
    an
    0.47
    ↵↵
    0.44
    has
    0.40
    p
    0.40
    να
    0.40
    ME
    0.40
    pra
    0.40
    K
    0.40
    Living
    0.40
    POSITIVE LOGITS
    <unused395>
    0.48
    。)
    0.47
    。\
    0.47
     ângulo
    0.46
    дт
    0.46
    دون
    0.46
     venge
    0.45
    ب
    0.45
    <unused706>
    0.44
     ángulo
    0.44
    Activations Density 0.000%

    No Known Activations