© 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. 236708
    Prev
    Next
    INDEX
    Explanations

    making or doing things

    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
    ru
    0.48
    <h2>
    0.46
    rat
    0.45
     hears
    0.44
    yska
    0.44
     говори
    0.43
    ime
    0.43
    red
    0.42
    Telefon
    0.41
    ing
    0.41
    POSITIVE LOGITS
     diffé
    0.47
     predictably
    0.45
    ِی
    0.42
    ਖ
    0.42
     onstage
    0.41
    レオ
    0.41
    த்திலும்
    0.40
     regista
    0.40
     percol
    0.39
     Praxis
    0.39
    Activations Density 0.000%

    No Known Activations