© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 113859
    Prev
    Next
    INDEX
    Explanations

    essential oil mix

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

    things that hadn’t been there

    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
    弁
    0.50
    ме
    0.47
    ն
    0.47
    owels
    0.45
     imme
    0.45
    𝘂
    0.45
    ларга
    0.44
     qualcosa
    0.43
     kısa
    0.43
     prenot
    0.43
    POSITIVE LOGITS
     Bundes
    0.48
     Hamburg
    0.48
     Globo
    0.46
     Gynecol
    0.46
    Ε
    0.45
     Grupo
    0.45
     Rancho
    0.44
    Hamburg
    0.43
     Frauen
    0.43
     Fatty
    0.43
    Activations Density 0.002%

    No Known Activations