© 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. 242796
    Prev
    Next
    INDEX
    Explanations

    their livelihood

    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
     settimane
    0.51
    亮
    0.50
    ヌ
    0.50
     titoli
    0.48
    班
    0.48
    抽
    0.48
     phép
    0.47
     tecnica
    0.46
    ように
    0.46
    撰
    0.46
    POSITIVE LOGITS
    s
    0.55
     في
    0.53
    ing
    0.52
     dishonest
    0.50
    Trail
    0.49
     उत्तरी
    0.49
     Float
    0.48
    ۔
    0.48
     ކ
    0.47
    ហេ
    0.47
    Activations Density 0.000%

    No Known Activations