© 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. 4191
    Prev
    Next
    INDEX
    Explanations

    how-to titles with numbers or experts

    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
    させて頂
    1.13
     Equival
    1.03
     ব্যতীত
    1.02
    ною
    1.00
    وبه
    1.00
    渉
    0.98
     періо
    0.97
    śl
    0.96
    非常的
    0.93
    )}=\
    0.93
    POSITIVE LOGITS
     billionaire
    1.62
    警方
    1.49
     politicians
    1.47
     lawmakers
    1.43
     crackdown
    1.34
     prosecutors
    1.33
     officials
    1.33
     ailing
    1.31
     rabbis
    1.30
    男人
    1.27
    Activations Density 0.456%

    No Known Activations