© 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. 64428
    Prev
    Next
    INDEX
    Explanations

    specific noun following article

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

    skin imperfections

    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
    k
    0.57
    r
    0.49
    os
    0.49
    p
    0.47
    w
    0.47
    <0xE2>
    0.44
    v
    0.44
     –
    0.43
    kc
    0.43
    vm
    0.43
    POSITIVE LOGITS
     plagues
    0.59
    కుండా
    0.52
     blemishes
    0.52
     flaws
    0.52
     rainbows
    0.50
    ัญหา
    0.50
     shortcomings
    0.49
     похађа
    0.49
     ugl
    0.48
    ائش
    0.48
    Activations Density 0.000%

    No Known Activations