© 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. 6894
    Prev
    Next
    INDEX
    Explanations

    pros and cons

    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
     ?
    1.16
     Panel
    1.14
     ï
    1.14
     MPC
    1.12
     panel
    1.06
     panels
    1.06
     !
    1.04
     persons
    1.03
     consid
    1.02
     notices
    1.02
    POSITIVE LOGITS
     megfelelő
    1.34
    孳
    1.27
    keszt
    1.27
    ądź
    1.24
    ambah
    1.22
    hető
    1.20
     زائدا
    1.16
    čiti
    1.16
     hátsó
    1.15
    uğu
    1.14
    Activations Density 0.021%

    No Known Activations