© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99909
    Prev
    Next
    INDEX
    Explanations

    multi-lingual diverse words

    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
    Not in Any Lists

    No Comments

    Negative Logits
     a
    -1.80
     of
    -1.63
    ꦺ
    -1.55
    توضی
    -1.55
     sério
    -1.55
    the
    -1.52
    葙
    -1.52
     empieza
    -1.52
    0
    -1.52
     suena
    -1.49
    POSITIVE LOGITS
     that
    2.34
     such
    1.98
    そんな
    1.73
    ラウンド
    1.52
    끄
    1.44
     такая
    1.40
     такую
    1.40
     таких
    1.38
     prachtig
    1.35
     opposed
    1.34
    Activations Density 0.002%

    No Known Activations