© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 239963
    Prev
    Next
    INDEX
    Explanations

    user home directories and folders

    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
     conval
    0.43
     certificación
    0.39
    perturbative
    0.38
    parametric
    0.37
    endtime
    0.37
    <0xCF>
    0.35
     kỷ
    0.35
     morf
    0.35
    ʀ
    0.35
     lectures
    0.35
    POSITIVE LOGITS
     personalise
    0.49
    空间的
    0.46
     espace
    0.45
    ్యంలో
    0.44
     пространство
    0.44
     encroachment
    0.44
     domaine
    0.43
     সরে
    0.42
    setRoot
    0.42
    Placed
    0.42
    Activations Density 0.055%

    No Known Activations