© 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. 15450
    Prev
    Next
    INDEX
    Explanations

    topics and titles

    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
     TÉCNICA
    -1.39
     their
    -1.39
     distritos
    -1.38
    際には
    -1.38
     hochwer
    -1.30
     these
    -1.27
    entibus
    -1.27
     گیاه
    -1.25
    iterranée
    -1.23
     violación
    -1.23
    POSITIVE LOGITS
     you
    2.89
     your
    2.66
     vám
    1.76
     You
    1.75
     вам
    1.73
    you
    1.67
    你
    1.61
     आपके
    1.51
     możesz
    1.47
    your
    1.43
    Activations Density 0.021%

    No Known Activations