© 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. 28291
    Prev
    Next
    INDEX
    Explanations

    book here

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

    n primes or Fibonacci

    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
    ת
    0.47
     ܗܘ
    0.46
    wearing
    0.46
    覺得
    0.45
    ME
    0.43
    clam
    0.43
     תו
    0.43
    疼
    0.42
    願意
    0.41
     Süden
    0.41
    POSITIVE LOGITS
    ında
    0.47
     Historic
    0.47
    历史
    0.45
     इंड
    0.45
    。
    0.44
    .\\
    0.44
    ۔
    0.43
     historic
    0.42
    ilación
    0.41
    ındaki
    0.41
    Activations Density 0.000%

    No Known Activations