© 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. 144976
    Prev
    Next
    INDEX
    Explanations

    attenuation factor, transport codes

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

    male presenting, fantasy fuels

    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
    glob
    0.52
     dihasil
    0.50
    ret
    0.49
    seen
    0.49
    not
    0.48
    o
    0.47
    nationality
    0.47
    groups
    0.47
    tariff
    0.46
     eurozone
    0.46
    POSITIVE LOGITS
    Pharmacy
    0.46
    Shr
    0.44
    维生素
    0.44
    们
    0.43
     ذكر
    0.43
    采样
    0.43
    剂量
    0.43
    Vocabulary
    0.43
    দিগের
    0.42
    Ethics
    0.42
    Activations Density 0.001%

    No Known Activations