© 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. 233881
    Prev
    Next
    INDEX
    Explanations

    legislature, congress, series, soviets

    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
     FAQs
    0.52
     ativa
    0.49
     c
    0.49
     TMZ
    0.42
     induc
    0.41
     ativos
    0.40
    PKG
    0.40
     kock
    0.40
     Herb
    0.40
    ometh
    0.39
    POSITIVE LOGITS
     ಆದ್ದರಿಂದ
    0.48
     αφού
    0.48
    ಭಾಗ
    0.47
     muttered
    0.46
     Đấy
    0.46
     σας
    0.45
    绞
    0.45
     rango
    0.44
    ബ്‌
    0.44
    ূর্ণ
    0.44
    Activations Density 0.000%

    No Known Activations