© 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. 43962
    Prev
    Next
    INDEX
    Explanations

    that is

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

    specifying attributes of 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
     அட்ட
    0.50
    jetas
    0.47
    чена
    0.47
     აღ
    0.45
    ক
    0.45
    raid
    0.45
     année
    0.45
     случаях
    0.44
    덮
    0.44
    cols
    0.44
    POSITIVE LOGITS
    grund
    0.52
    暖
    0.45
     scorpion
    0.44
     gospod
    0.44
    Commons
    0.44
    入門
    0.44
     comune
    0.43
     maju
    0.43
     Scorpion
    0.43
    ُل
    0.42
    Activations Density 0.000%

    No Known Activations