© 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. 35206
    Prev
    Next
    INDEX
    Explanations

    modifying carburetor

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

    poetry and AI

    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
    និយាយ
    0.54
    ழிய
    0.47
    onomi
    0.47
    akkhati
    0.47
     некоторое
    0.46
     ٹرسٹ
    0.46
     unterschied
    0.45
    兘
    0.45
     পিঁপড়ার
    0.45
    িয়াছে
    0.45
    POSITIVE LOGITS
    ↵
    0.48
    .
    0.45
     AF
    0.44
     TI
    0.42
    :'
    0.41
     Ethiop
    0.41
     AFM
    0.41
     Jiu
    0.40
     ISO
    0.39
    0.39
    Activations Density 0.000%

    No Known Activations