© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 14412
    Prev
    Next
    INDEX
    Explanations

    not a professional

    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
     Brexit
    2.49
     onboarding
    2.44
     🙂
    2.40
     KPIs
    2.35
     cashback
    2.32
     cheeky
    2.28
     bespoke
    2.26
    Brexit
    2.23
     跟
    2.23
     maths
    2.22
    POSITIVE LOGITS
    又は
    1.69
    ologic
    1.56
    Oklahoma
    1.46
     congressional
    1.43
    Alabama
    1.42
     Oklahoma
    1.39
     appellee
    1.38
     accomplishes
    1.36
     histologic
    1.36
    rologic
    1.34
    Activations Density 0.154%

    No Known Activations