© 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. 114418
    Prev
    Next
    INDEX
    Explanations

    Federal Republic

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

    Not identical

    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
    same
    0.54
    ag
    0.53
    ana
    0.52
    im
    0.50
    াজ
    0.49
    bx
    0.48
    p
    0.48
     PMID
    0.47
    y
    0.47
    pura
    0.46
    POSITIVE LOGITS
     Dessous
    0.47
     zupeł
    0.47
     الطعام
    0.46
     völlig
    0.44
     میان
    0.43
    微软
    0.43
     Grundlagen
    0.42
    浥
    0.42
     طبیعی
    0.42
     Gefahr
    0.42
    Activations Density 0.001%

    No Known Activations