© 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. 65665
    Prev
    Next
    INDEX
    Explanations

    Code/Math structure symbols

    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
     sessão
    -1.02
    kiwa
    -0.99
     fundador
    -0.97
     publicó
    -0.93
     esperança
    -0.92
    somewhat
    -0.91
     malah
    -0.90
    various
    -0.90
     erzeugt
    -0.90
     geralmente
    -0.90
    POSITIVE LOGITS
     increased
    1.05
     will
    0.96
     more
    0.92
     further
    0.90
    نا
    0.89
     from
    0.88
     by
    0.88
    も同じ
    0.85
    TEEN
    0.84
     with
    0.84
    Activations Density 0.002%

    No Known Activations