© 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. 172838
    Prev
    Next
    INDEX
    Explanations

    omega-3, best, international

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

    discovering new knowledge

    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
    adım
    0.50
    heiten
    0.50
    явления
    0.47
    wellery
    0.46
     божомолдор
    0.46
    Ĵ
    0.46
    ag
    0.45
    alis
    0.45
    (__
    0.44
    aların
    0.44
    POSITIVE LOGITS
    ógrafo
    0.47
     ১৯৪৭
    0.45
     Barriers
    0.45
     degli
    0.45
     所有
    0.45
     dicembre
    0.44
     catalyze
    0.43
     الشي
    0.43
     Airplane
    0.43
     Mound
    0.43
    Activations Density 0.000%

    No Known Activations