© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 8883
    Prev
    Next
    INDEX
    Explanations

    model assignment and comparison

    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
    tao
    1.38
     blood
    1.35
    ე
    1.31
    ten
    1.29
     point
    1.27
    ting
    1.27
    dong
    1.23
     call
    1.19
    ted
    1.19
     post
    1.18
    POSITIVE LOGITS
    ுமா
    1.49
     Auswahl
    1.39
    ه
    1.32
     zum
    1.30
     carrito
    1.28
    żli
    1.26
    plash
    1.25
    zinho
    1.24
    arası
    1.24
    人不
    1.24
    Activations Density 0.000%

    No Known Activations