© 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. 164626
    Prev
    Next
    INDEX
    Explanations

    inventory, commercial, trailers, soul

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

    order and its rating

    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
    cover
    0.49
    gles
    0.49
    c
    0.46
    ges
    0.46
    shan
    0.45
    explain
    0.45
     دیکھیں
    0.45
    color
    0.45
    dev
    0.44
    hens
    0.44
    POSITIVE LOGITS
     прогнозы
    0.52
     bolje
    0.47
     беремен
    0.47
     soja
    0.47
     брау
    0.46
     좋아
    0.46
     фаса
    0.46
    ﺽ
    0.46
     জে
    0.45
     військо
    0.45
    Activations Density 0.000%

    No Known Activations