© 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. 252027
    Prev
    Next
    INDEX
    Explanations

    language diversity and specific terms

    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
    ês
    0.55
    组
    0.53
    之后
    0.49
    ès
    0.49
    Trên
    0.49
    Speaking
    0.48
    ocsát
    0.48
    出
    0.48
     αυτά
    0.48
    选取
    0.47
    POSITIVE LOGITS
     candied
    0.48
     pH
    0.48
     trabalhadores
    0.47
    waveform
    0.45
     minim
    0.45
     renormal
    0.45
     terbaik
    0.44
    pH
    0.44
     proton
    0.44
     reagent
    0.44
    Activations Density 0.000%

    No Known Activations