© 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. 10356
    Prev
    Next
    INDEX
    Explanations

    compile code instructions

    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
    TO
    2.71
    TRA
    2.33
    AsStream
    2.23
    phones
    2.13
    <bos>
    2.12
    bedded
    2.05
    GIS
    2.03
     titular
    2.03
     стекло
    2.02
     trừ
    2.00
    POSITIVE LOGITS
     handleError
    2.74
    λ
    2.48
     numquam
    2.45
    ্লিশ
    2.28
    sad
    2.27
    ────
    2.27
    sı
    2.26
    िसिटी
    2.22
    sar
    2.22
    aş
    2.22
    Activations Density 0.155%

    No Known Activations