© 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. 4417
    Prev
    Next
    INDEX
    Explanations

    API and AI

    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
    quoi
    2.31
    oscopic
    2.27
    bands
    2.18
    ځ
    2.12
    precio
    2.11
    finals
    2.10
    lah
    2.08
     locu
    2.06
    seit
    2.06
    ாவது
    2.05
    POSITIVE LOGITS
    s
    2.90
    ی
    2.36
    İ
    2.14
    에
    2.11
    ING
    2.07
    一手
    1.95
    İM
    1.95
    ុន
    1.95
    illet
    1.91
    І
    1.91
    Activations Density 0.610%

    No Known Activations