© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12620
    Prev
    Next
    INDEX
    Explanations

    git merge conflict markers and decoration

    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
    ractions
    1.95
    raction
    1.94
     tình
    1.94
    reb
    1.75
    르
    1.74
    っきり
    1.74
     clinical
    1.73
     intermission
    1.68
    acc
    1.68
     mortem
    1.67
    POSITIVE LOGITS
    규
    2.57
    畊
    2.35
     runApp
    2.18
    PasswordField
    2.16
     persegi
    2.15
    Glide
    2.13
    ︎
    2.13
     smatra
    2.12
    SearchResult
    2.08
    uxxxx
    2.06
    Activations Density 0.030%

    No Known Activations