© 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. 9319
    Prev
    Next
    INDEX
    Explanations

    introducing contrast or consequence

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

    emphasizing key information

    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
     رہی
    0.27
     Екатери
    0.27
    ﺪ
    0.25
    ただし
    0.23
    ाय
    0.23
    将军
    0.23
    $.)
    0.23
     দেখিলাম
    0.23
     variously
    0.23
    ανά
    0.23
    POSITIVE LOGITS
     nunca
    0.37
     they
    0.36
     never
    0.34
     nigdy
    0.34
    ak
    0.33
     niemand
    0.33
    ை
    0.33
     ninguna
    0.32
     siempre
    0.32
     I
    0.32
    Activations Density 0.301%

    No Known Activations