© 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. 44183
    Prev
    Next
    INDEX
    Explanations

    fashion styles

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

    product style categories

    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
     도시
    0.55
    kében
    0.55
     የመጀመሪያ
    0.52
    vať
    0.52
     одном
    0.51
    熾
    0.51
     imprecise
    0.51
    間に
    0.50
    orderHint
    0.50
    кта
    0.50
    POSITIVE LOGITS
    ,
    0.59
     bile
    0.59
    2
    0.59
     je
    0.52
    ide
    0.51
     show
    0.51
    ’
    0.50
    ed
    0.50
    RI
    0.50
    PL
    0.50
    Activations Density 0.000%

    No Known Activations