© 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. 201633
    Prev
    Next
    INDEX
    Explanations

    honestly, chosen, leads

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

    explaining technical concepts

    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
    gy
    0.50
     Milan
    0.47
     Stuttgart
    0.47
     NEO
    0.47
     Valentino
    0.47
     GLOBAL
    0.47
     reis
    0.46
    <0x0D>
    0.44
     Chengdu
    0.44
     Frankfurt
    0.44
    POSITIVE LOGITS
    রোধ
    0.50
    ৬
    0.48
    SQL
    0.46
     sposob
    0.44
    лло
    0.42
     পরিশোধ
    0.42
    ناف
    0.42
    ᖃ
    0.41
     chiqar
    0.41
     alimentaire
    0.40
    Activations Density 0.000%

    No Known Activations