© 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. 13-GEMMASCOPE-2-RES-16K
    7. 5761
    Prev
    Next
    INDEX
    Explanations

    temperature ranges and values

    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_13_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
    в
    1.64
    Shortly
    1.57
    room
    1.56
     Shortly
    1.47
    After
    1.46
    Almost
    1.43
    MRP
    1.42
    −
    1.41
     ০
    1.41
    ium
    1.39
    POSITIVE LOGITS
     adolesc
    1.71
    uangan
    1.57
     fasteners
    1.50
    揣
    1.49
     wygl
    1.48
     Standardization
    1.48
     berhubungan
    1.48
     alakalı
    1.47
     genders
    1.47
     standardization
    1.47
    Activations Density 0.073%

    No Known Activations