© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58064
    Prev
    Next
    INDEX
    Explanations

    nature of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Anſ
    -2.55
    ﻂ
    -2.16
    derdag
    -2.16
    pruch
    -2.13
     relatif
    -2.11
     ſy
    -2.11
     eſſ
    -2.08
    旆
    -2.08
     ſever
    -2.06
    跸
    -2.05
    POSITIVE LOGITS
     quickly
    2.19
    j
    2.19
    ul
    2.17
    re
    2.16
     these
    2.08
     if
    1.84
    0
    1.83
    em
    1.81
    at
    1.81
    彼の
    1.80
    Activations Density 0.008%

    No Known Activations