© 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. 5483
    Prev
    Next
    INDEX
    Explanations

    SAMHSA

    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
    fait
    2.39
    zás
    2.32
    ười
    2.21
     թ
    2.16
    ś
    2.16
    zus
    2.14
    cı
    2.11
    ھار
    2.11
    o
    2.10
    рный
    2.07
    POSITIVE LOGITS
    ून्य
    4.53
    ৃঙ্খ
    3.60
    anigans
    3.42
    ारीरिक
    3.40
    ایط
    3.31
    ब्दिक
    3.12
    ঙ্খ
    3.11
    idefinite
    3.04
    isticated
    3.00
    erialize
    3.00
    Activations Density 0.958%

    No Known Activations