© 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. 15580
    Prev
    Next
    INDEX
    Explanations

    instructions for running code

    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
     misconception
    1.28
    Ι
    1.26
    KNOWN
    1.21
    Α
    1.19
     분야
    1.19
    Ens
    1.18
     기반
    1.18
    REQUIRE
    1.17
     Α
    1.16
    Reasons
    1.16
    POSITIVE LOGITS
     resten
    1.09
    amus
    1.04
     chale
    1.03
    ophyllum
    1.00
    otch
    0.96
    üd
    0.95
    üsse
    0.92
    ú
    0.92
     tá
    0.91
    ärt
    0.90
    Activations Density 0.021%

    No Known Activations