© 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. 22-GEMMASCOPE-RES-131K
    7. 64590
    Prev
    Next
    INDEX
    Explanations

    code snippets and structures

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /
    -0.99
    vané
    -0.96
    бражение
    -0.93
    の紹介
    -0.92
    の概要
    -0.90
     россия
    -0.86
    -
    -0.86
    当たり前
    -0.85
    クリル
    -0.85
     démocr
    -0.84
    POSITIVE LOGITS
     paroisse
    1.01
     keduanya
    0.93
    ceder
    0.92
    曲目
    0.91
     Während
    0.90
    рока
    0.90
    φαλ
    0.88
     Maggiore
    0.88
     خارجية
    0.86
    IMENTS
    0.86
    Activations Density 0.018%

    No Known Activations