© 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. 11606
    Prev
    Next
    INDEX
    Explanations

    desert, processing, accuracy

    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
    raz
    1.60
    aino
    1.27
    acon
    1.27
    ᵛ
    1.26
    اج
    1.23
    owel
    1.23
    rai
    1.23
     främ
    1.22
    ал
    1.21
    idi
    1.21
    POSITIVE LOGITS
    Quite
    1.57
    バシー
    1.51
    宕
    1.45
     devenu
    1.41
     renversement
    1.40
     turno
    1.40
    isasi
    1.39
    elizmente
    1.39
     Quite
    1.38
    NuGet
    1.38
    Activations Density 0.000%

    No Known Activations