© 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. 14778
    Prev
    Next
    INDEX
    Explanations

    "if i were to ask"

    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
    ما
    1.85
    ্ধ্য
    1.84
    容
    1.77
    ༥
    1.67
    वटी
    1.64
     mücade
    1.62
     unique
    1.60
    ゙
    1.60
    要
    1.60
    رو
    1.58
    POSITIVE LOGITS
    '\
    1.95
    tes
    1.92
    czyk
    1.90
     échange
    1.87
    ginas
    1.79
     ácido
    1.75
    pv
    1.74
     おり
    1.72
     "-//
    1.71
     Algarve
    1.68
    Activations Density 0.001%

    No Known Activations