© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 130784
    Prev
    Next
    INDEX
    Explanations

    emojis and dessert

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     पुलिस
    0.45
     kolon
    0.41
     полицей
    0.41
     calcula
    0.41
     polícia
    0.41
     mínimo
    0.40
     policías
    0.40
    ꯠ
    0.40
     ಪೊಲೀ
    0.39
     contenedor
    0.39
    POSITIVE LOGITS
     viss
    0.38
    seats
    0.37
    球
    0.37
     strolling
    0.36
    sports
    0.36
     stroll
    0.35
    Sports
    0.35
    utiérrez
    0.34
    Joyce
    0.34
    Storm
    0.34
    Activations Density 0.002%

    No Known Activations