© 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. 184950
    Prev
    Next
    INDEX
    Explanations

    mechanical tooth

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

    technical words and phrases

    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
     главного
    0.55
     hechos
    0.53
    ида
    0.52
    ленных
    0.51
    ка
    0.50
     variegated
    0.50
    кту
    0.49
     亀
    0.49
     главных
    0.49
     জিনিস
    0.49
    POSITIVE LOGITS
    t
    0.48
    GT
    0.45
    restriction
    0.43
    Gent
    0.43
    銀座
    0.42
    TEA
    0.41
    NaN
    0.41
    Restriction
    0.41
    tub
    0.41
    Throw
    0.40
    Activations Density 0.000%

    No Known Activations