© 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. 139655
    Prev
    Next
    INDEX
    Explanations

    numbers and specific terms

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

    different phases, immediately after, human demographics

    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
    ﺭ
    0.53
    ب
    0.51
    ﺃ
    0.47
    ren
    0.47
    am
    0.46
    Inc
    0.46
    ब
    0.46
    ﺩ
    0.46
     परामर्श
    0.46
    Program
    0.46
    POSITIVE LOGITS
     marginalised
    0.50
     brus
    0.49
     crochet
    0.49
     postavlj
    0.47
    뒀
    0.47
    刺繍
    0.46
     qubits
    0.46
     Rembrandt
    0.46
     quinine
    0.45
     Sada
    0.45
    Activations Density 0.000%

    No Known Activations