© 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. 11379
    Prev
    Next
    INDEX
    Explanations

    Fair or wait

    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
    c
    3.63
    r
    3.41
    n
    3.06
    l
    2.95
    m
    2.84
    CreateParams
    2.78
    ು
    2.70
    nh
    2.69
    nya
    2.69
    𝐜
    2.68
    POSITIVE LOGITS
    edas
    3.13
    উন্ট
    3.03
    یین
    2.95
    КА
    2.86
    resham
    2.76
    дження
    2.69
    礁
    2.66
     त्यस
    2.65
    𝑠
    2.64
    ിച്ച്
    2.64
    Activations Density 0.002%

    No Known Activations