© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 1074
    Prev
    Next
    INDEX
    Explanations

    questions about doing things in 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_65k_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
     pinching
    1.14
    inducing
    1.10
    <unused925>
    1.07
     grossly
    1.06
    <unused1839>
    1.06
    BEFORE
    1.05
    xcuser
    1.05
     suffices
    1.05
    throwing
    1.03
    <unused902>
    1.03
    POSITIVE LOGITS
    株式会社
    1.18
     situado
    1.18
     Company
    1.15
     Corporation
    1.05
     společnosti
    1.05
    ita
    1.05
     Institute
    1.03
     Boutique
    1.03
     Brothers
    1.02
     compañía
    1.01
    Activations Density 0.747%

    No Known Activations