© 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. 7-GEMMASCOPE-2-RES-16K
    7. 3482
    Prev
    Next
    INDEX
    Explanations

    code execution and file paths

    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
    ات
    1.85
    یە
    1.73
    sü
    1.70
    s
    1.66
    ه
    1.63
     باش
    1.59
    sourced
    1.59
    ز
    1.57
    эм
    1.56
     محک
    1.55
    POSITIVE LOGITS
     descanso
    2.08
     actuality
    2.02
     finances
    1.98
     vacation
    1.97
     amortization
    1.96
     Treasure
    1.93
     clearTimeout
    1.90
     treasure
    1.83
     concealed
    1.82
     foreclosure
    1.78
    Activations Density 0.032%

    No Known Activations