© 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. 14735
    Prev
    Next
    INDEX
    Explanations

    a deliberate parts

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

    bread and buns

    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
     すぎ
    0.44
     აღ
    0.43
    ara
    0.43
     す
    0.43
     бү
    0.43
     ар
    0.42
     ช
    0.42
     れ
    0.41
     張
    0.41
    ৃত্তি
    0.41
    POSITIVE LOGITS
     insiders
    0.51
     eyewear
    0.48
     BTW
    0.46
    يمي
    0.46
     negócio
    0.45
     backstory
    0.45
     marketplaces
    0.44
    BTW
    0.44
     ecommerce
    0.44
     coworking
    0.43
    Activations Density 0.000%

    No Known Activations