© 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. 101460
    Prev
    Next
    INDEX
    Explanations

    mechanical numbers and parts

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

    sections with numbers or roman numerals

    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
    €
    0.46
    /${
    0.44
     sayısı
    0.42
    !=
    0.39
    💂
    0.39
    
    0.39
    值为
    0.38
    豸
    0.38
    此类
    0.38
    iseren
    0.38
    POSITIVE LOGITS
     DV
    0.39
    ácie
    0.38
    fonte
    0.38
    the
    0.38
    uí
    0.35
    pais
    0.35
    something
    0.34
     wygląd
    0.34
     foams
    0.34
    hout
    0.34
    Activations Density 0.023%

    No Known Activations