© 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. 1973
    Prev
    Next
    INDEX
    Explanations

    machine operand, key manager, memory slot

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

    Fibonacci, dataFrom, eventAddress, displayValue, quickselect

    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
    IRCONIUM
    0.34
    бря
    0.31
    桡
    0.30
    WING
    0.29
    aminated
    0.29
    RADIATION
    0.28
     हिमालय
    0.28
     священ
    0.28
    槨
    0.28
    ніх
    0.28
    POSITIVE LOGITS
     ?>
    0.26
     time
    0.26
     fortune
    0.26
     tracker
    0.26
    .<
    0.26
     we
    0.25
     shipments
    0.25
     precaution
    0.25
     paperwork
    0.25
    weiser
    0.25
    Activations Density 0.007%

    No Known Activations