© 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. 80605
    Prev
    Next
    INDEX
    Explanations

    rehabilitative rule efficient tropical dimension long-term intentions

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

    rooted in

    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
     muebles
    0.53
     danych
    0.52
    ós
    0.51
    bezpie
    0.51
    vané
    0.50
    ら
    0.49
     drugiej
    0.48
    맏
    0.48
     приготовления
    0.46
    AR
    0.46
    POSITIVE LOGITS
    ယ်
    0.49
    ذه
    0.48
     قانون
    0.45
    公斤
    0.45
     lis
    0.45
     दाग
    0.44
    لوث
    0.43
     تصور
    0.42
     جز
    0.42
     )
    0.42
    Activations Density 0.000%

    No Known Activations