© 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. 3102
    Prev
    Next
    INDEX
    Explanations

    code constructs and JSON parsing

    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
    ારીખ
    2.80
     настрой
    2.68
    टीएस
    2.64
    ϡ
    2.59
    𒄷
    2.58
     consideramos
    2.57
    mathspace
    2.53
    𒁹
    2.53
    琙
    2.52
     Difer
    2.51
    POSITIVE LOGITS
    getitem
    2.10
    <em>
    1.96
    osing
    1.88
    번에
    1.87
     b
    1.83
    실
    1.83
     bug
    1.81
    0
    1.74
    3
    1.73
    <bos>
    1.73
    Activations Density 0.073%

    No Known Activations