© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 9797
    Prev
    Next
    INDEX
    Explanations

    time, location, or specific details

    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
    t
    1.11
    sid
    1.11
    sing
    1.10
    ubine
    1.10
    tos
    1.08
    tong
    1.08
    sb
    1.07
    s
    1.05
    sr
    1.05
    ો
    1.03
    POSITIVE LOGITS
     Beberapa
    1.43
     سایر
    1.40
     다양한
    1.37
     பல்வேறு
    1.37
     Meskipun
    1.36
     Imágenes
    1.35
     ಅಥವಾ
    1.34
     Plusieurs
    1.33
     környez
    1.32
     أو
    1.32
    Activations Density 0.000%

    No Known Activations