© 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. 13-GEMMASCOPE-2-RES-16K
    7. 13679
    Prev
    Next
    INDEX
    Explanations

    code block terminators

    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_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
    1.49
    ed
    1.15
     or
    1.06
     S
    1.04
     knowledge
    1.04
     o
    1.02
    ”
    1.01
     rest
    1.01
     P
    1.00
     felt
    1.00
    POSITIVE LOGITS
     Highness
    1.83
    UInteger
    1.80
     município
    1.78
     ArrayRef
    1.78
    <unused464>
    1.77
     IUnary
    1.76
     fieldContext
    1.75
    <unused278>
    1.75
     координаты
    1.74
    alámb
    1.71
    Activations Density 0.002%

    No Known Activations