© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 244537
    Prev
    Next
    INDEX
    Explanations

    punctuation, however, ideally

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     variantes
    0.53
     thé
    0.52
     alternativas
    0.51
     téléphone
    0.50
     améliorer
    0.50
    ᓐ
    0.50
     convient
    0.49
    욌
    0.49
     générations
    0.49
     lít
    0.49
    POSITIVE LOGITS
     Cambodia
    0.50
     Wu
    0.47
     Diarsipkan
    0.46
    asana
    0.46
    alab
    0.45
    effects
    0.45
    chemia
    0.44
     Caucasus
    0.44
    Arrows
    0.44
    equilibrium
    0.43
    Activations Density 0.000%

    No Known Activations