© 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. 231782
    Prev
    Next
    INDEX
    Explanations

    paying for something

    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
    環境
    0.48
    ↵
    0.47
    圖片
    0.47
     cirk
    0.46
    種
    0.45
    delt
    0.44
    {%
    0.44
    }+{
    0.44
    像是
    0.44
    羅
    0.43
    POSITIVE LOGITS
     upperBound
    0.56
     escog
    0.54
     haces
    0.54
    wają
    0.52
     edifício
    0.50
    ądź
    0.50
    ಷ್ಠ
    0.49
     caballo
    0.49
     شریف
    0.49
     indeterm
    0.49
    Activations Density 0.002%

    No Known Activations