© 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. 86424
    Prev
    Next
    INDEX
    Explanations

    financial terms and extensions

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

    cult favorite classic figure

    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
    ᱐
    0.53
     sectores
    0.51
    opathological
    0.50
     inhomogeneities
    0.47
    গতি
    0.47
    id
    0.46
     espaces
    0.46
     espacios
    0.45
     cambios
    0.45
    }_{\
    0.45
    POSITIVE LOGITS
     Maschine
    0.54
    更是
    0.50
     الدكتور
    0.47
     بود
    0.47
    بيق
    0.46
     ალ
    0.46
    الو
    0.46
    赶紧
    0.45
    立即
    0.44
    ئو
    0.44
    Activations Density 0.001%

    No Known Activations