© 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. 64930
    Prev
    Next
    INDEX
    Explanations

    code functions and file operations

    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
    次回は
    -1.04
    czo
    -0.91
     najdete
    -0.90
    ³)
    -0.88
     kürzlich
    -0.87
     therefore
    -0.84
     hierfür
    -0.83
     použ
    -0.82
    ではまた
    -0.81
     Ache
    -0.81
    POSITIVE LOGITS
    ській
    0.94
    ündete
    0.93
    zmir
    0.91
     runde
    0.90
     DVDs
    0.89
     Deum
    0.89
    pplung
    0.89
    さらに
    0.89
     dönt
    0.88
     kram
    0.88
    Activations Density 0.004%

    No Known Activations