© 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. 70046
    Prev
    Next
    INDEX
    Explanations

    Ventajas, AAA, Seats, Turn, eggs

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

    code snippets and URLs

    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
    Michael
    0.37
    nocześnie
    0.37
    Caution
    0.36
     MICHAEL
    0.35
    michael
    0.34
     michael
    0.34
    痠
    0.33
    ichael
    0.33
     Michael
    0.33
    ارف
    0.33
    POSITIVE LOGITS
    垠
    0.38
     (,
    0.36
     மட்டுமே
    0.35
    нци
    0.34
     শ্রেণি
    0.34
     করিতেছি
    0.34
    量は
    0.34
     उपलब्धि
    0.33
     ञ
    0.33
     mortem
    0.32
    Activations Density 0.078%

    No Known Activations