© 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. 60722
    Prev
    Next
    INDEX
    Explanations

    — followed by proper nouns

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

    citizens or culturally

    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
    教師
    0.62
    訓練
    0.48
    이에요
    0.45
     гер
    0.45
    <h3>
    0.44
    INTE
    0.43
    ssr
    0.43
    Saya
    0.42
    О
    0.42
    護
    0.42
    POSITIVE LOGITS
     lediglich
    0.51
     ciudadanos
    0.51
     welcher
    0.50
     citoyens
    0.49
     diligently
    0.48
     Zusätzlich
    0.47
     cittadini
    0.47
    ാള
    0.46
    ದ್ದರಿಂದ
    0.46
     دوسروں
    0.46
    Activations Density 0.000%

    No Known Activations