© 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. 226550
    Prev
    Next
    INDEX
    Explanations

    acquiring an estimate

    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
    Negative Logits
    ایی
    0.50
    ऍ
    0.47
    으면
    0.46
    ualitas
    0.46
    ownic
    0.46
    axis
    0.46
    지와
    0.46
    जीवी
    0.45
    kowania
    0.45
    ﻚ
    0.45
    POSITIVE LOGITS
    ீக
    0.53
     Woolf
    0.52
     tries
    0.52
     uncertainties
    0.47
     digesting
    0.47
     attempts
    0.47
     উদ্যোগ
    0.47
     approximations
    0.46
     contradictions
    0.46
     Mining
    0.46
    Activations Density 0.000%

    No Known Activations