© 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. 103942
    Prev
    Next
    INDEX
    Explanations

    numbers and dates

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

    Lewis, Ireland, Allies

    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
    当时的
    0.52
    extré
    0.49
     είχε
    0.45
    睪
    0.45
    病情
    0.44
    origData
    0.44
     τότε
    0.44
    钀
    0.43
     Immunol
    0.43
     triglycer
    0.43
    POSITIVE LOGITS
     А
    0.44
     crawling
    0.43
     bashing
    0.43
     summons
    0.41
     вчера
    0.40
     opens
    0.40
    а
    0.40
     amaç
    0.39
    гӀ
    0.39
     используют
    0.39
    Activations Density 0.000%

    No Known Activations