© 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. 7-GEMMASCOPE-2-RES-16K
    7. 13642
    Prev
    Next
    INDEX
    Explanations

    javascript function calls

    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
     tangente
    2.16
    を送
    2.02
    ಪ್ಪು
    1.96
     самая
    1.95
     merhabalar
    1.91
    ек
    1.91
    ㄣ
    1.90
    ený
    1.90
     prestataire
    1.89
    থিল
    1.89
    POSITIVE LOGITS
     floor
    1.86
     final
    1.53
     &
    1.50
     floors
    1.47
     premises
    1.45
     terrain
    1.42
     Final
    1.40
     Floor
    1.40
     and
    1.35
    floor
    1.35
    Activations Density 0.000%

    No Known Activations