© 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. 42584
    Prev
    Next
    INDEX
    Explanations

    non-english words

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

    numbers, lists, or options

    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
    on
    0.63
    ONG
    0.53
    ের
    0.49
    อก
    0.47
     («
    0.46
     Qaeda
    0.45
     (
    0.44
    ASS
    0.44
    対応
    0.44
    s
    0.44
    POSITIVE LOGITS
     tři
    0.59
     três
    0.53
     trzy
    0.52
     realização
    0.52
     zuverläss
    0.51
    ிருக்க
    0.49
     composição
    0.49
     čty
    0.49
    čení
    0.48
     për
    0.48
    Activations Density 0.000%

    No Known Activations