© 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. 13-GEMMASCOPE-2-RES-16K
    7. 6820
    Prev
    Next
    INDEX
    Explanations

    parental guidance options

    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
     private
    1.03
     Fuss
    1.03
     Private
    1.02
     laughing
    1.02
    בן
    1.01
     PRIVATE
    1.00
     겨
    1.00
     जगदीश
    0.98
     eingesch
    0.98
     wick
    0.97
    POSITIVE LOGITS
    unitary
    1.35
    beest
    1.32
    embark
    1.31
    planar
    1.30
    locations
    1.30
    presentation
    1.29
    pictured
    1.24
    kości
    1.23
    kość
    1.23
    ұ
    1.22
    Activations Density 0.000%

    No Known Activations