© 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. 1679
    Prev
    Next
    INDEX
    Explanations

    rewriting or rephrasing text

    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
     vial
    2.15
     vials
    2.05
     `./
    1.97
    oop
    1.95
    𝘶
    1.95
     getNodeId
    1.90
    ὺς
    1.87
    odule
    1.83
     cabling
    1.83
     lager
    1.83
    POSITIVE LOGITS
    ي
    2.31
    সিডেন্ট
    1.98
    স্পষ্ট
    1.95
    भावना
    1.94
    Abandon
    1.93
    ษัท
    1.91
    I
    1.89
    ع
    1.89
    間
    1.87
    Gesch
    1.86
    Activations Density 0.030%

    No Known Activations