© 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. 33507
    Prev
    Next
    INDEX
    Explanations

    years ending

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

    making steak au poivre

    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
    ন
    0.53
    ή
    0.50
    כר
    0.50
    λάβ
    0.47
    لیف
    0.46
    DECLARE
    0.46
    Section
    0.45
    i
    0.45
     STATUS
    0.45
     पुरस्कृत
    0.45
    POSITIVE LOGITS
     disruptions
    0.51
     disappointments
    0.50
     orifices
    0.47
    rino
    0.46
     unbear
    0.44
     annoyance
    0.43
     فنا
    0.43
     為
    0.43
     integrals
    0.42
     เห
    0.42
    Activations Density 0.000%

    No Known Activations