© 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. 218539
    Prev
    Next
    INDEX
    Explanations

    what typewhat works

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

    colon followed by space

    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
     worry
    0.52
    ÇÃO
    0.50
     yaşam
    0.50
     cherish
    0.48
     pë
    0.48
     surviv
    0.48
     پایان
    0.47
    Š
    0.47
     merken
    0.47
     quantified
    0.47
    POSITIVE LOGITS
     Hanks
    0.48
    adds
    0.46
    afio
    0.46
     Sheets
    0.43
     -$
    0.43
    ধন
    0.42
     Moser
    0.42
     McManus
    0.42
    ovy
    0.42
    可以让
    0.42
    Activations Density 0.000%

    No Known Activations