© 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. 10675
    Prev
    Next
    INDEX
    Explanations

    roadmap headings

    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
     以及
    1.59
    ριο
    1.46
    또한
    1.45
     Tracks
    1.34
     අව
    1.33
     或
    1.32
     또한
    1.31
     数据
    1.31
     ܘ
    1.30
     πραγμα
    1.30
    POSITIVE LOGITS
    leur
    1.24
    ler
    1.24
    lice
    1.17
    menu
    1.14
    nului
    1.13
    workers
    1.12
    lady
    1.10
    lire
    1.10
    worker
    1.10
    ↵↵
    1.06
    Activations Density 0.181%

    No Known Activations