© 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. 22241
    Prev
    Next
    INDEX
    Explanations

    placeholders and future content

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

    placeholder, inf, NaN, unknown

    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
    🚜
    0.50
     ویئر
    0.44
    ahanan
    0.43
     နှစ်
    0.42
     tuyên
    0.42
     Sử
    0.41
     உருவாக்கி
    0.40
     nettoyer
    0.40
     Fron
    0.39
    劦
    0.39
    POSITIVE LOGITS
     unattainable
    0.47
     prices
    0.47
     placeholder
    0.45
     infinity
    0.43
     коли
    0.42
     смерть
    0.42
    maz
    0.40
     placeholders
    0.40
     death
    0.40
    hile
    0.40
    Activations Density 0.001%

    No Known Activations