© 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. 3424
    Prev
    Next
    INDEX
    Explanations

    various languages and programming 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_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
    𓂃
    1.44
     omgeving
    1.40
    দিক
    1.39
     bâtiment
    1.35
     ketogenic
    1.33
    ायल
    1.33
    চ্ছন্ন
    1.32
     stru
    1.31
    𝙀
    1.31
    τει
    1.31
    POSITIVE LOGITS
    湎
    1.81
     POLL
    1.79
    ipherals
    1.75
    corder
    1.72
    MEMORY
    1.72
     ש
    1.72
     Не
    1.72
     Jest
    1.72
     Memory
    1.69
    prints
    1.68
    Activations Density 0.000%

    No Known Activations