© 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. 10235
    Prev
    Next
    INDEX
    Explanations

    dates following "On"

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

    commemorating historical events

    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
    ru
    0.54
    rock
    0.50
    to
    0.48
    vý
    0.48
    ryw
    0.46
    essie
    0.45
    rand
    0.45
    o
    0.45
    end
    0.44
    toff
    0.44
    POSITIVE LOGITS
     cryptographic
    0.53
     configuring
    0.52
     అనేది
    0.51
     arbitr
    0.50
     imageData
    0.50
     appending
    0.49
     താ
    0.48
     reduzir
    0.48
     calibration
    0.48
     اندراج
    0.47
    Activations Density 0.000%

    No Known Activations