© 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. 22-GEMMASCOPE-RES-131K
    7. 128982
    Prev
    Next
    INDEX
    Explanations

    words starting with 'Cor' or 'Cor' followed by punctuation

    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
    ktioner
    -1.06
     bianche
    -1.04
    tillation
    -0.95
    サンプル
    -0.93
    íg
    -0.93
    樣子
    -0.92
     mélang
    -0.91
    enschein
    -0.90
     caribou
    -0.88
    有时
    -0.88
    POSITIVE LOGITS
    neuri
    1.09
    bilde
    1.06
     laranja
    0.98
    karta
    0.98
    bouts
    0.98
     limpar
    0.95
    issu
    0.91
    aure
    0.91
    warf
    0.91
    hermosa
    0.89
    Activations Density 0.002%

    No Known Activations