© 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. 7594
    Prev
    Next
    INDEX
    Explanations

    data representations

    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
     douze
    1.20
     zes
    1.18
    ذة
    1.17
    埶
    1.16
     zwölf
    1.11
     dao
    1.10
     الدوري
    1.10
     sechs
    1.10
    茦
    1.10
     шесть
    1.10
    POSITIVE LOGITS
     Abend
    0.91
     Sunday
    0.86
    sunday
    0.85
    day
    0.82
    Sunday
    0.82
    grid
    0.79
     conta
    0.79
     Saturday
    0.79
    Saturday
    0.77
     on
    0.77
    Activations Density 0.103%

    No Known Activations