© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 54444
    Prev
    Next
    INDEX
    Explanations

    every noun

    np_acts-logits-general · gemini-2.5-flash-lite

    every unique instance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     for
    1.25
     are
    1.00
    is
    0.94
    are
    0.91
    of
    0.89
    ี
    0.84
     of
    0.84
     the
    0.84
    ă
    0.82
    ى
    0.82
    POSITIVE LOGITS
    0
    0.88
    其他
    0.86
    に
    0.86
    every
    0.77
    ที่
    0.76
    toon
    0.75
    ทุก
    0.74
    name
    0.72
     Every
    0.71
    df
    0.71
    Activations Density 0.053%

    No Known Activations