© 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. 124502
    Prev
    Next
    INDEX
    Explanations

    Star at

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

    more rugged, complete, rather, village, to, from, term, hidden, can

    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
    t
    0.73
     Eligible
    0.59
     Updates
    0.56
    ໍ່
    0.49
    easing
    0.48
     Nursing
    0.48
     Medications
    0.48
     Opportunities
    0.47
     Allergy
    0.46
     Preschool
    0.46
    POSITIVE LOGITS
     চম
    0.49
     ジェ
    0.47
     ሃ
    0.47
     كس
    0.45
     ジャ
    0.45
     見
    0.45
    WinCounter
    0.45
     patitth
    0.45
     dazz
    0.44
    ChangeListener
    0.44
    Activations Density 0.001%

    No Known Activations