© 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. 7963
    Prev
    Next
    INDEX
    Explanations

    a difference

    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
    %/
    1.31
     entornos
    1.20
    웠
    1.18
     intents
    1.10
     modalities
    1.08
     내용을
    1.07
     向
    1.07
     주요
    1.07
     WIDTH
    1.06
     contexts
    1.06
    POSITIVE LOGITS
    éges
    1.23
     Clare
    1.12
     cuadrado
    1.02
    felder
    1.01
     Challenger
    1.01
    ály
    0.99
     caj
    0.95
    hur
    0.95
     Bazar
    0.95
    mud
    0.94
    Activations Density 0.025%

    No Known Activations