© 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. 161430
    Prev
    Next
    INDEX
    Explanations

    academic progress, websites, managed, concentrated

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

    Hungarian heritage

    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
     الگ
    0.42
     البروت
    0.42
    Expend
    0.41
    亢
    0.41
    Résumé
    0.41
    OUND
    0.40
    Dollars
    0.40
     حرام
    0.40
    PRESSED
    0.40
    Jaw
    0.39
    POSITIVE LOGITS
    startsWith
    0.47
    𝟭
    0.47
     можем
    0.45
     putem
    0.45
     maneiras
    0.45
    urig
    0.44
    asını
    0.44
     tendremos
    0.44
     verfügbar
    0.44
    leşik
    0.43
    Activations Density 0.000%

    No Known Activations