© 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. 22-GEMMASCOPE-2-RES-16K
    7. 10593
    Prev
    Next
    INDEX
    Explanations

    a qualified

    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_22_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
    mán
    0.90
     老
    0.87
     nain
    0.86
    nian
    0.86
    xiii
    0.86
    funcionario
    0.85
     सब्स
    0.85
    <unused730>
    0.85
    thern
    0.85
    ServiceObject
    0.84
    POSITIVE LOGITS
     sixteen
    0.77
     reindeer
    0.75
    ఋ
    0.71
    แ
    0.71
    ते
    0.70
    ACI
    0.70
     wchar
    0.69
    Interceptor
    0.68
     Temper
    0.67
    itsi
    0.66
    Activations Density 0.140%

    No Known Activations