© 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. 73410
    Prev
    Next
    INDEX
    Explanations

    ticket or transmission or festive

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

    evaluations, schedules, offers, search

    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
    ervlak
    0.44
    定義
    0.44
    ⛷
    0.44
    ーーーー
    0.43
    ።
    0.43
     البنات
    0.43
     repe
    0.42
    ંત્રી
    0.42
    َ
    0.42
     će
    0.41
    POSITIVE LOGITS
    ज
    0.46
    恴
    0.45
     Eff
    0.44
     Threshold
    0.43
     Rien
    0.43
     Dove
    0.42
    高考
    0.42
     Cracked
    0.41
     क्रॉप
    0.41
    borhood
    0.41
    Activations Density 0.000%

    No Known Activations