© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 2728
    Prev
    Next
    INDEX
    Explanations

    return statement

    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_65k_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
     horrend
    1.14
     notoriously
    1.14
     买
    1.14
     procured
    1.11
    <unused2103>
    1.11
    <unused290>
    1.10
     교
    1.10
     grossly
    1.10
     cruel
    1.09
     goblin
    1.09
    POSITIVE LOGITS
     итоге
    0.91
    +(
    0.84
     +
    0.84
    +
    0.83
    <eos>
    0.82
    +".
    0.81
     +(
    0.81
    これで
    0.80
    Combined
    0.79
    มากกว่า
    0.79
    Activations Density 0.110%

    No Known Activations