© 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. 101646
    Prev
    Next
    INDEX
    Explanations

    descriptive pairings and follow-ups

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

    is,

    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
     売
    0.52
     स्रोत
    0.47
    ٹنگ
    0.46
    𝚖
    0.46
     વિકાસ
    0.44
    য়ার
    0.44
     مدی
    0.44
    تھی
    0.44
    স্তর
    0.44
    𝒊
    0.44
    POSITIVE LOGITS
     multipl
    0.52
     lockout
    0.49
    痊
    0.47
     annulus
    0.47
     ADJUST
    0.46
     fullness
    0.46
     abnorm
    0.46
     книга
    0.45
     verhind
    0.44
     circumfer
    0.44
    Activations Density 0.002%

    No Known Activations