© 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. 14563
    Prev
    Next
    INDEX
    Explanations

    dynamic states or actions

    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
     heartbreak
    1.16
    timeline
    1.12
     timeline
    1.12
    s
    1.11
     pity
    1.11
    aron
    1.11
    ronic
    1.09
     heartache
    1.09
    aaaa
    1.05
     vistazo
    1.03
    POSITIVE LOGITS
    宾
    1.40
    噹
    1.34
    addington
    1.21
     penyeleng
    1.20
    ৃত্তি
    1.17
    及其
    1.17
     pelaksanaan
    1.17
    ถาน
    1.14
     convened
    1.13
    +{\
    1.13
    Activations Density 0.000%

    No Known Activations