© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 3558
    Prev
    Next
    INDEX
    Explanations

    an inside joke

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_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
    ož
    2.14
     cookieParser
    2.05
    枱
    2.00
     prévention
    1.99
     abordagem
    1.97
    nydd
    1.89
    arcía
    1.87
     carriera
    1.85
     buộc
    1.85
     ElevatedButton
    1.84
    POSITIVE LOGITS
     وخ
    2.09
    كي
    1.97
    讧
    1.80
    ׁ
    1.72
    fera
    1.66
    দ্য
    1.63
    insi
    1.63
    涵
    1.58
     دل
    1.57
    irit
    1.57
    Activations Density 0.509%

    No Known Activations