© 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. 221038
    Prev
    Next
    INDEX
    Explanations

    eliminate it or fill it

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

    start of 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
    Negative Logits
     airlift
    0.53
     churn
    0.46
     biel
    0.45
    榇
    0.45
     Hassel
    0.45
    ʏ
    0.44
     तरीके
    0.44
     Berth
    0.44
     mAbs
    0.44
     Fateh
    0.44
    POSITIVE LOGITS
    ﻨ
    0.48
    אר
    0.47
    uniformly
    0.46
    IDENTITY
    0.45
    ciamo
    0.45
     erroneously
    0.45
    侨
    0.44
    consistency
    0.44
    stationary
    0.44
    Representatives
    0.44
    Activations Density 0.001%

    No Known Activations