© 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. 127226
    Prev
    Next
    INDEX
    Explanations

    degree, enough, convert

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

    implied exploitation; love of fate

    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
    眸
    0.47
    lept
    0.46
     التربيع
    0.45
    答应
    0.45
     생각이
    0.44
    实施
    0.43
     ওয়াল
    0.43
    导弹
    0.43
     점점
    0.42
     وخت
    0.42
    POSITIVE LOGITS
     a
    0.48
     the
    0.46
     sails
    0.46
     facere
    0.44
     Philips
    0.43
     $
    0.42
     exp
    0.42
     parishes
    0.42
    Op
    0.42
     countable
    0.41
    Activations Density 0.000%

    No Known Activations