© 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. 221658
    Prev
    Next
    INDEX
    Explanations

    literature of, trends of, numbers have been, store when, is correct, SAG Awards, positive number, someone who, encouraging me

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

    desire to commit

    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
    эф
    0.52
    々
    0.49
    々は
    0.47
    ня
    0.47
    годня
    0.46
    ні
    0.46
    ープ
    0.46
    мыс
    0.46
    ゎ
    0.46
    导致
    0.45
    POSITIVE LOGITS
    erve
    0.47
    NumConst
    0.46
    alco
    0.46
     neuf
    0.46
    halle
    0.46
    huis
    0.45
     Elektrokhimiya
    0.44
     आपूर्ति
    0.44
     beri
    0.44
    acteur
    0.43
    Activations Density 0.001%

    No Known Activations