© 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. 38047
    Prev
    Next
    INDEX
    Explanations

    Freeport Maine

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

    places and research topics

    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
     ing
    0.50
    A
    0.47
     Clark
    0.46
     M
    0.44
     Storia
    0.44
     மொத்தம்
    0.44
     Io
    0.43
     Thành
    0.43
     contributors
    0.43
     Álvarez
    0.43
    POSITIVE LOGITS
     пытается
    0.54
    ждает
    0.47
    研修
    0.45
     יכול
    0.45
    theoretical
    0.45
    पहरण
    0.45
     жо
    0.44
     худо
    0.44
    髖
    0.44
    所謂
    0.44
    Activations Density 0.000%

    No Known Activations