© 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. 14227
    Prev
    Next
    INDEX
    Explanations

    database references and animal associations

    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
    aloo
    1.15
    atee
    1.13
    韭
    1.10
    alit
    1.08
    ruvic
    1.07
    江
    1.07
    crackers
    1.04
    խ
    1.04
     liquors
    1.04
    asic
    1.03
    POSITIVE LOGITS
     lingkungan
    1.56
     terlihat
    1.51
     pengg
    1.49
     yaitu
    1.48
     ponownie
    1.46
     sesuai
    1.44
     kedua
    1.44
     terlebih
    1.44
     pengelolaan
    1.43
     seluruh
    1.42
    Activations Density 0.002%

    No Known Activations