© 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. 152246
    Prev
    Next
    INDEX
    Explanations

    waste, removal, or neighbors

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

    list or outline points

    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
    如果没有
    0.46
    fé
    0.45
    Eventually
    0.44
     orgánica
    0.43
    怼
    0.43
     πλη
    0.43
     "@
    0.42
    =@
    0.42
    −
    0.41
    jk
    0.40
    POSITIVE LOGITS
     missionary
    0.54
     engender
    0.50
     subcluster
    0.46
     poświę
    0.46
    मिस्ट्री
    0.45
     segmental
    0.45
     empir
    0.44
    وامی
    0.44
     Missionary
    0.44
     dedication
    0.44
    Activations Density 0.000%

    No Known Activations