© 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. 98348
    Prev
    Next
    INDEX
    Explanations

    common sequences

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

    emojis and punctuation!

    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
     taint
    0.51
     attrib
    0.47
     delays
    0.47
     accu
    0.47
    โทษ
    0.46
     unjust
    0.46
     blames
    0.46
    -
    0.45
     absol
    0.44
     outright
    0.44
    POSITIVE LOGITS
    ре
    0.57
     ঝ
    0.55
    的东西
    0.51
     во
    0.49
     карто
    0.47
     канал
    0.47
    濩
    0.46
    де
    0.46
     море
    0.46
    вовано
    0.45
    Activations Density 0.001%

    No Known Activations