© 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. 148668
    Prev
    Next
    INDEX
    Explanations

    collection of or related to merchandise

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

    human intervention

    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
    l
    0.47
    ല്ല
    0.45
    ោក
    0.43
    t
    0.42
     Ar
    0.41
    demos
    0.41
    s
    0.41
    浜
    0.41
     demonstrates
    0.40
     biologic
    0.40
    POSITIVE LOGITS
    ੱਚ
    0.54
    rası
    0.49
     propi
    0.49
     大きい
    0.48
     dysplasia
    0.48
    GradientPanel
    0.47
    参
    0.47
     вообще
    0.46
     thisobject
    0.46
    érieures
    0.46
    Activations Density 0.000%

    No Known Activations