© 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. 13752
    Prev
    Next
    INDEX
    Explanations

    existence

    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
    ্ষ
    2.26
    ４
    2.08
     mắn
    2.07
    ško
    2.05
    ５
    2.03
    ಸ್ಸ
    2.02
    ๕
    2.01
    ８
    2.00
    ７
    2.00
    이드
    1.97
    POSITIVE LOGITS
    тен
    2.16
     orde
    2.13
    тента
    2.08
    uate
    2.04
    na
    2.04
    リート
    2.03
     holes
    2.01
     pockets
    2.00
     hole
    1.99
     empl
    1.98
    Activations Density 0.032%

    No Known Activations