© 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. 86248
    Prev
    Next
    INDEX
    Explanations

    teaching, available, and hand

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

    URL, revisions, test

    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
     détail
    0.54
     comté
    0.51
     zwięks
    0.49
     ধাত
    0.49
    φέρει
    0.48
     Харків
    0.48
    鈦
    0.48
     contrôler
    0.48
     Storia
    0.48
     Villages
    0.47
    POSITIVE LOGITS
    ចេញ
    0.54
    จะไม่
    0.47
    eko
    0.47
    បង្ហាញ
    0.46
    eye
    0.46
    say
    0.45
    \/
    0.45
    -+
    0.45
    ARD
    0.44
    law
    0.44
    Activations Density 0.000%

    No Known Activations