© 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. 12124
    Prev
    Next
    INDEX
    Explanations

    Express train or sat perched

    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
     Junta
    1.14
     Licenses
    1.10
     Premi
    1.09
     PhoneNumber
    1.08
     Deleg
    1.01
    祐
    1.01
     Township
    1.00
     Electrode
    0.99
     Operator
    0.97
     Admin
    0.96
    POSITIVE LOGITS
     ভাইরাল
    1.25
    ̨
    1.22
    ervis
    1.18
    abeled
    1.14
    Madison
    1.14
    folk
    1.13
    тернет
    1.13
    Columbus
    1.13
    Brasil
    1.11
     отече
    1.11
    Activations Density 0.012%

    No Known Activations