© 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. 201335
    Prev
    Next
    INDEX
    Explanations

    maintenance information

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

    website with

    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
    ohn
    0.48
    ј
    0.48
    น
    0.46
    ոն
    0.46
    ן
    0.46
     అతని
    0.46
    νον
    0.45
    ↵
    0.45
    滿
    0.45
    aban
    0.45
    POSITIVE LOGITS
     sporty
    0.51
     STM
    0.51
     from
    0.51
     traumatic
    0.49
     Nang
    0.49
     Trần
    0.48
     zing
    0.48
     Aga
    0.48
     zonas
    0.48
     Komfort
    0.47
    Activations Density 0.001%

    No Known Activations