© 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. 31658
    Prev
    Next
    INDEX
    Explanations

    currency exchange

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

    mathematical expression equals sign

    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
     /\
    0.44
     altid
    0.43
     उल्टा
    0.42
     Versus
    0.41
    /\
    0.41
    停止
    0.40
     CR
    0.40
    vs
    0.39
     المنطقة
    0.37
    /^
    0.37
    POSITIVE LOGITS
     라는
    0.48
     prosa
    0.48
    awah
    0.46
    ństwo
    0.44
    浆
    0.41
     mundane
    0.41
    jalan
    0.39
     выяс
    0.39
     വസ്തു
    0.39
     jurisdictions
    0.39
    Activations Density 0.002%

    No Known Activations