© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12050
    Prev
    Next
    INDEX
    Explanations

    diaphragmatic breathing, humanitarian pause

    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_7_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
    े
    3.02
    o
    2.94
    ean
    2.64
    eaa
    2.63
    a
    2.61
    ebe
    2.53
    aura
    2.48
    e
    2.43
    瓈
    2.43
    eed
    2.38
    POSITIVE LOGITS
    न्नाथ
    2.18
     signOut
    2.17
    вшие
    2.15
    াপ
    2.07
    лись
    1.95
    лась
    1.95
    klich
    1.93
    ́t
    1.90
    ynchronously
    1.90
    اتھن
    1.89
    Activations Density 0.007%

    No Known Activations