© 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. 39534
    Prev
    Next
    INDEX
    Explanations

    machine code or settling dust

    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
    不会
    0.48
    <0xB7>
    0.45
    Би
    0.43
    Access
    0.43
    chainId
    0.41
    这种情况
    0.41
    Walking
    0.40
    Nonetheless
    0.40
    clusión
    0.40
    齜
    0.40
    POSITIVE LOGITS
     forn
    0.50
     rinsing
    0.48
     finite
    0.48
    iyat
    0.47
     pigmented
    0.46
     underweight
    0.46
     sump
    0.46
    neet
    0.46
     durg
    0.46
     nourishment
    0.45
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.