© 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. 212862
    Prev
    Next
    INDEX
    Explanations

    sentence ending punctuation

    np_acts-logits-general · gemini-2.5-flash-lite

    hosting localization clarity

    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
    বিহীন
    0.47
    裸
    0.47
    ненко
    0.46
     kleines
    0.46
     Patrim
    0.45
     ব্যান
    0.44
    nicu
    0.44
    Πα
    0.44
    íc
    0.43
     Arbeiten
    0.43
    POSITIVE LOGITS
    "।
    0.51
     DETAIL
    0.46
    "،
    0.46
    an
    0.45
     enablement
    0.44
    ";
    0.44
    ".[
    0.44
    "."
    0.44
    ان
    0.44
    :";
    0.44
    Activations Density 0.001%

    No Known Activations