© 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. 83785
    Prev
    Next
    INDEX
    Explanations

    time, holidays, past, or future

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

    classic comedy; is like; was a

    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
    いった
    0.58
    ड
    0.50
    AUG
    0.49
    Banks
    0.49
    ड्
    0.46
    ଡ
    0.46
    survey
    0.46
    thed
    0.46
    sense
    0.46
    tage
    0.45
    POSITIVE LOGITS
     russian
    0.48
     fling
    0.47
    etzte
    0.46
     entice
    0.46
     ills
    0.45
    স্‌
    0.45
     scrumptious
    0.45
     ἐ
    0.44
     hilarious
    0.44
    іл
    0.44
    Activations Density 0.000%

    No Known Activations