© 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. 244449
    Prev
    Next
    INDEX
    Explanations

    story starts

    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
    dependency
    0.45
     ಸಂಗೀತ
    0.45
     фонда
    0.44
     reputable
    0.43
    depend
    0.42
    妛
    0.42
     мүмк
    0.41
     வர
    0.41
    
    0.41
     Министерство
    0.41
    POSITIVE LOGITS
     uważ
    0.50
    ciata
    0.46
    Looks
    0.46
     Nes
    0.44
     Lug
    0.44
     Wilt
    0.44
    Ziel
    0.43
     Delgado
    0.43
     accueillir
    0.43
     Tires
    0.43
    Activations Density 0.000%

    No Known Activations