© 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. 203144
    Prev
    Next
    INDEX
    Explanations

    crypto-currency and hydrogen refueling

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

    cash back match, model independence, smart city, slides, suggestions

    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
     장애
    0.52
     경영
    0.50
     בש
    0.48
     ราศี
    0.47
     לצ
    0.47
    Fourier
    0.47
     ሕ
    0.46
     기본적인
    0.46
    将军
    0.46
     hinder
    0.46
    POSITIVE LOGITS
    a
    0.48
    aj
    0.47
     a
    0.46
    AK
    0.45
    ajj
    0.45
     you
    0.45
     Very
    0.44
    UK
    0.43
    اما
    0.43
    сы
    0.42
    Activations Density 0.000%

    No Known Activations