© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 12256
    Prev
    Next
    INDEX
    Explanations

    degrees Celsius, historical average, limited

    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
     ส
    1.14
     أ
    1.13
     แบบ
    1.10
    แบบ
    1.10
     بشكل
    1.08
    การ
    1.08
     وهو
    1.07
    ح
    1.05
     وهذا
    1.03
     وين
    1.02
    POSITIVE LOGITS
    혀
    1.09
     energies
    1.08
     segu
    1.07
     wisdom
    1.07
     enthusiasm
    1.02
     astute
    1.01
     plod
    1.00
     motiv
    1.00
     obe
    0.99
     madres
    0.98
    Activations Density 0.000%

    No Known Activations