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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 70472
    Prev
    Next
    INDEX
    Explanations

    generated by

    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
     baratas
    -1.26
    noční
    -1.24
    timb
    -1.24
    ieR
    -1.23
     blancas
    -1.23
     睡
    -1.23
     climático
    -1.22
    kursi
    -1.19
     negras
    -1.17
     pistola
    -1.16
    POSITIVE LOGITS
     Sortiment
    1.36
    veness
    1.23
    脸上的
    1.19
     unangemessene
    1.18
    brtc
    1.17
    vetica
    1.16
     sämtliche
    1.16
     dieselben
    1.14
    leyball
    1.14
    ar
    1.14
    Activations Density 0.001%

    No Known Activations