Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 3608
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     бы
    2.65
     solid
    2.33
    نك
    2.20
     mower
    1.92
    嵘
    1.82
    adien
    1.81
     winch
    1.78
    ാത്ത
    1.77
    ن
    1.77
    стью
    1.76
    POSITIVE LOGITS
    NSY
    3.52
    *********
    3.33
    *************
    3.27
    ******
    3.13
    ****************
    3.12
    ***********
    3.05
    ************
    3.02
    sigh
    3.02
    **************
    3.02
    cough
    2.95
    Activations Density 0.023%

    No Known Activations