© 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. 128342
    Prev
    Next
    INDEX
    Explanations

    quantity or occurrences

    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
    nede
    -1.04
     PREVIOUS
    -1.02
     différents
    -1.02
     éven
    -0.97
     fique
    -0.97
     corações
    -0.96
     eene
    -0.96
    PREVIOUS
    -0.96
    ఝ
    -0.95
     précédent
    -0.93
    POSITIVE LOGITS
     Numerous
    1.06
     numerous
    1.04
     constantly
    1.04
     tries
    1.03
     eleven
    0.98
     steadily
    0.97
     countless
    0.96
     дисци
    0.95
     innumerable
    0.94
     unquestionably
    0.94
    Activations Density 0.080%

    No Known Activations