© 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. 12222
    Prev
    Next
    INDEX
    Explanations

    simple, easy, quick to implement

    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
     abond
    2.00
     portare
    1.96
    ೖ
    1.85
     affront
    1.84
    factorplot
    1.84
    厭
    1.83
     portato
    1.82
    脹
    1.81
     dwind
    1.80
    crate
    1.79
    POSITIVE LOGITS
     세
    1.66
    েম্ব
    1.64
    ما
    1.63
     Именно
    1.61
    ity
    1.60
    الية
    1.60
     se
    1.50
     le
    1.49
     طل
    1.49
     اقد
    1.48
    Activations Density 0.152%

    No Known Activations