© 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. 188977
    Prev
    Next
    INDEX
    Explanations

    film or awareness

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

    purchasing 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
    ه
    0.47
     Strukturen
    0.46
     Rezept
    0.45
     underneath
    0.43
     वन्य
    0.42
     Studenten
    0.41
     verwendet
    0.41
    ත
    0.41
     Einstellungen
    0.40
     किंवा
    0.40
    POSITIVE LOGITS
     synthes
    0.47
     بسي
    0.46
    cok
    0.46
    olesale
    0.45
     mái
    0.45
    𝒃
    0.44
     CAGR
    0.44
     eml
    0.44
     ର
    0.44
    kinson
    0.43
    Activations Density 0.001%

    No Known Activations