© 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. 72117
    Prev
    Next
    INDEX
    Explanations

    modern furniture

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

    bad, sometimes, average

    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
    PRODUCT
    0.48
    (\|
    0.47
     PRODUCT
    0.46
    =====
    0.45
    inston
    0.44
    kező
    0.44
    ক
    0.44
     পাচ্ছি
    0.44
     pizzas
    0.43
     describing
    0.42
    POSITIVE LOGITS
    协调
    0.45
     Koordin
    0.44
     öz
    0.44
     ندارد
    0.43
    協
    0.41
     koordin
    0.41
     чове
    0.40
     Verantwortung
    0.39
     شك
    0.39
     ندار
    0.39
    Activations Density 0.000%

    No Known Activations