© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130506
    Prev
    Next
    INDEX
    Explanations

    months in dates

    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
     its
    -0.91
    支持
    -0.86
    Its
    -0.82
     тол
    -0.82
     måneder
    -0.79
    āju
    -0.78
     ži
    -0.77
     Erden
    -0.76
     faucet
    -0.75
     kanskje
    -0.74
    POSITIVE LOGITS
     again
    0.93
    zsche
    0.90
     PUBLISHED
    0.88
    ffy
    0.86
     baixo
    0.84
    PROVID
    0.84
     ocasião
    0.83
     जारी
    0.82
    veloppe
    0.82
    つた
    0.82
    Activations Density 0.002%

    No Known Activations