© 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. 16429
    Prev
    Next
    INDEX
    Explanations

    null terminators

    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
    にほんブログ村
    -1.09
    眼下
    -1.08
    ならではの
    -1.07
     estableció
    -1.06
     than
    -1.05
    詫
    -1.04
    warnai
    -1.04
     desarrollando
    -1.02
     сегодняш
    -1.02
     plaît
    -0.99
    POSITIVE LOGITS
    wirkungen
    1.04
     qualquer
    0.93
     plus
    0.91
    TeX
    0.90
    男性
    0.89
     fich
    0.89
    起源
    0.89
    𝓽
    0.89
     _,
    0.88
    ࣪
    0.88
    Activations Density 0.005%

    No Known Activations