© 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. 31-GEMMASCOPE-2-RES-262K
    7. 205540
    Prev
    Next
    INDEX
    Explanations

    concepts and context

    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_31_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
    ak
    0.50
    чити
    0.49
    家
    0.48
     terapia
    0.47
    zia
    0.46
    ディガン
    0.46
    等級
    0.45
    ură
    0.44
    umbi
    0.44
    लक्ष
    0.44
    POSITIVE LOGITS
    ’
    0.43
     thinker
    0.42
     compactly
    0.42
    >:
    0.41
     chunk
    0.41
    CAT
    0.40
    ޟ
    0.40
    $:
    0.40
     Bracket
    0.39
     chrét
    0.39
    Activations Density 0.004%

    No Known Activations