© 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. 79027
    Prev
    Next
    INDEX
    Explanations

    relationships, science, time, and events

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

    technical descriptions and concepts

    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
    níka
    0.49
     perishable
    0.46
     بنایا
    0.46
    紆
    0.45
     있어
    0.45
    sommets
    0.45
    촤
    0.45
    perror
    0.45
     verdens
    0.45
    áver
    0.45
    POSITIVE LOGITS
     Wolverine
    0.50
    ת
    0.47
     Fior
    0.46
    ,
    0.46
    Quote
    0.46
    ي
    0.46
     YouTube
    0.46
     Spot
    0.45
    Subscribe
    0.45
    денти
    0.45
    Activations Density 0.000%

    No Known Activations