© 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. 12740
    Prev
    Next
    INDEX
    Explanations

    programming, code, or logic

    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
     extraneous
    1.53
    <unused298>
    1.45
     inconsistent
    1.45
     prescriptive
    1.42
    multer
    1.32
     inflexible
    1.31
    stackpath
    1.31
    rparam
    1.31
     permiss
    1.30
     induc
    1.29
    POSITIVE LOGITS
    フ
    1.47
     layanan
    1.46
     conferma
    1.46
     antiguo
    1.45
     seluruh
    1.43
     Terbaru
    1.40
     confirmó
    1.39
     rusak
    1.38
    ocsát
    1.38
     afirmó
    1.38
    Activations Density 0.000%

    No Known Activations