© 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. 10615
    Prev
    Next
    INDEX
    Explanations

    charset =

    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
     centerY
    2.80
    ꯤ
    2.61
    getConfiguration
    2.60
    ennzeichnet
    2.59
     পরিস্কার
    2.58
    circulation
    2.58
    vention
    2.57
    দের
    2.54
    ﮄ
    2.54
    ULTURAL
    2.54
    POSITIVE LOGITS
    وجد
    2.87
    ton
    2.46
    rate
    2.43
    E
    2.43
    ালী
    2.27
     let
    2.25
    hentication
    2.24
     chặn
    2.16
    नी
    2.16
     paro
    2.15
    Activations Density 0.005%

    No Known Activations