© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 1030
    Prev
    Next
    INDEX
    Explanations

    heard correctly

    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_65k_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
    owlapi
    2.03
    mathspace
    1.70
    paysys
    1.69
    葢
    1.65
    countery
    1.61
     vattum
    1.59
    <unused1233>
    1.56
     gstlal
    1.55
     ARRAY
    1.54
    querysearch
    1.52
    POSITIVE LOGITS
    0
    1.64
    2
    1.48
    1
    1.44
    3
    1.43
    4
    1.42
    9
    1.37
    7
    1.34
    6
    1.31
    5
    1.28
    世紀
    1.27
    Activations Density 0.629%

    No Known Activations