© 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. 206793
    Prev
    Next
    INDEX
    Explanations

    burglar is

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

    professional advice or structure

    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
     grilling
    0.52
     vás
    0.49
     people
    0.46
     tradicional
    0.44
     tolerate
    0.44
    羢
    0.43
     vite
    0.43
     ger
    0.43
     scammers
    0.42
     verkaufen
    0.42
    POSITIVE LOGITS
    ⚕
    0.45
     кілька
    0.43
     विमान
    0.42
    ufthansa
    0.42
    几次
    0.42
    اوز
    0.41
     বিমানের
    0.41
     несколько
    0.41
    poem
    0.41
    ಟ್‌
    0.41
    Activations Density 0.001%

    No Known Activations