© 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. 3642
    Prev
    Next
    INDEX
    Explanations

    knowledge retrieval

    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
    y
    3.31
    ers
    2.52
    ی
    2.44
    აზ
    2.43
    similarity
    2.37
    rig
    2.34
    rj
    2.32
    ен
    2.32
    樫
    2.31
    ്ട
    2.31
    POSITIVE LOGITS
    deleteAll
    3.23
    Elater
    2.80
    躇
    2.59
    اليا
    2.54
     kế
    2.41
     말미암
    2.41
    Descripcion
    2.35
     MongoClient
    2.35
    faat
    2.33
    চিতে
    2.31
    Activations Density 0.249%

    No Known Activations