© 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. 148926
    Prev
    Next
    INDEX
    Explanations

    those.

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

    describing content contextually

    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
    ફેદ
    0.54
    莨
    0.51
     кабе
    0.50
    了一声
    0.49
    ଫ
    0.48
     नाइट्र
    0.48
    夰
    0.48
    ়া
    0.48
     mạng
    0.47
     Badajoz
    0.47
    POSITIVE LOGITS
    displayed
    0.52
    background
    0.51
    ږد
    0.50
    pres
    0.49
    merge
    0.48
    variety
    0.47
    kte
    0.47
    provided
    0.47
    subject
    0.46
    standards
    0.46
    Activations Density 0.001%

    No Known Activations