© 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. 11800
    Prev
    Next
    INDEX
    Explanations

    nothing works

    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
     Ша
    1.58
     Ли
    1.48
     Ю
    1.47
     Де
    1.47
     Чи
    1.40
     也
    1.40
    ruptcy
    1.37
    plier
    1.37
    fact
    1.34
     אי
    1.34
    POSITIVE LOGITS
     sním
    1.09
     pertemuan
    1.01
     stazione
    1.00
     zcela
    0.99
     benda
    0.96
    掻
    0.95
     společ
    0.95
     honom
    0.93
    iamo
    0.92
     fotografías
    0.91
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.