© 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. 7-GEMMASCOPE-2-RES-16K
    7. 11713
    Prev
    Next
    INDEX
    Explanations

    you or someone you know

    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_7_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
     functionally
    1.36
    ansion
    1.35
    سته
    1.31
     preserve
    1.31
     affected
    1.28
     chlorides
    1.25
    ation
    1.23
     [
    1.21
    lemish
    1.19
     resolution
    1.19
    POSITIVE LOGITS
    ワク
    1.98
     öss
    1.95
     iskust
    1.92
     experiencia
    1.91
    bindingNavigator
    1.90
     experiência
    1.89
     nascita
    1.89
     dieci
    1.88
    Ꮔ
    1.87
     empecé
    1.86
    Activations Density 0.186%

    No Known Activations