© 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. 11436
    Prev
    Next
    INDEX
    Explanations

    referrals to local services

    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
     bö
    1.25
     Diskussion
    1.24
     wesentlich
    1.23
     Như
    1.23
     mágico
    1.22
     很
    1.17
     새로
    1.16
    新的
    1.16
     besonders
    1.16
     खूप
    1.15
    POSITIVE LOGITS
    amantha
    1.18
    nt
    1.17
    odiac
    1.14
    ни
    1.13
    athery
    1.11
    stit
    1.07
    muj
    1.07
    rać
    1.00
    lig
    0.99
    designated
    0.98
    Activations Density 0.000%

    No Known Activations