© 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. 143743
    Prev
    Next
    INDEX
    Explanations

    seasons and locations

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

    Enlightenment, forcing, energy, foundation

    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
    퍽
    0.46
    Especially
    0.44
    Launched
    0.44
    Sincerely
    0.43
    بوب
    0.43
    ，
    0.43
     служба
    0.43
    Already
    0.42
    مث
    0.42
     парт
    0.42
    POSITIVE LOGITS
    }}=-\
    0.54
     pozosta
    0.52
     Omicron
    0.48
     veranda
    0.48
    ยนตร์
    0.48
     যাওয়ার
    0.47
    tr
    0.46
     outright
    0.46
    vp
    0.46
    rugated
    0.46
    Activations Density 0.001%

    No Known Activations