© 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. 45482
    Prev
    Next
    INDEX
    Explanations

    listing #

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

    recognizes / refused / Reads

    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
     inaugur
    0.49
     Ayurvedic
    0.49
    纰
    0.49
     ی
    0.48
     coerc
    0.47
     Immac
    0.46
     AI
    0.46
     airfoil
    0.46
    डम
    0.46
     elucid
    0.46
    POSITIVE LOGITS
    ését
    0.50
    áciu
    0.48
    obut
    0.48
    ésil
    0.47
    r
    0.46
    ónde
    0.46
    ábamos
    0.46
    locked
    0.45
    лят
    0.45
    সন্ত
    0.44
    Activations Density 0.002%

    No Known Activations