© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 34639
    Prev
    Next
    INDEX
    Explanations

    regex and code structure

    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
    an
    0.71
    '
    0.70
    on
    0.69
    ’
    0.67
    ا
    0.63
    お
    0.61
    お金
    0.60
     공유
    0.59
    ان
    0.58
    াধিক
    0.58
    POSITIVE LOGITS
    nél
    0.83
     ໜ
    0.72
    cię
    0.71
    illä
    0.70
    şiv
    0.69
    řich
    0.69
     tenía
    0.68
     nettement
    0.68
     inscripción
    0.68
     términos
    0.68
    Activations Density 0.001%

    No Known Activations