© 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. 2717
    Prev
    Next
    INDEX
    Explanations

    Yes, absolutely

    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
    ạm
    1.83
    ર
    1.81
    𝐢
    1.74
    tir
    1.73
    ceso
    1.73
    cwnd
    1.69
    tic
    1.67
    tss
    1.65
    thiophene
    1.62
    %%%%%%%%
    1.56
    POSITIVE LOGITS
     plane
    1.28
     verpflicht
    1.22
     TE
    1.19
     teas
    1.17
    Innen
    1.15
     protectors
    1.12
    佥
    1.10
     imply
    1.10
    setRoot
    1.09
    settes
    1.09
    Activations Density 0.000%

    No Known Activations