© 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. 139826
    Prev
    Next
    INDEX
    Explanations

    equal status

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

    directives and suggestions

    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
     coast
    0.46
     Oracle
    0.46
     tél
    0.46
    ահ
    0.45
    ە
    0.45
     Mathemat
    0.45
     Chemical
    0.45
     Statistical
    0.44
    قت
    0.44
    ক্ষা
    0.44
    POSITIVE LOGITS
    urred
    0.45
    d
    0.45
    tract
    0.44
    aday
    0.44
     기름
    0.44
    of
    0.44
    liness
    0.44
    kitten
    0.44
     silverware
    0.43
    rill
    0.42
    Activations Density 0.000%

    No Known Activations