© 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. 7221
    Prev
    Next
    INDEX
    Explanations

    period of brilliancy

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

    qualifications, force, motion, inhabitants

    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
     هستند
    0.78
     கட்டமை
    0.75
    ্যান্ড
    0.73
    銠
    0.73
     Latinoamérica
    0.73
     அவரின்
    0.71
    𐰚
    0.71
    评估
    0.71
     سیستم
    0.70
     సమయంలో
    0.70
    POSITIVE LOGITS
     effectually
    0.90
     workmen
    0.83
     scanty
    0.83
     trifling
    0.80
     innumerable
    0.80
     thence
    0.78
     peculiarly
    0.78
     ſ
    0.76
     scarcely
    0.76
     negroes
    0.76
    Activations Density 0.137%

    No Known Activations