© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 7112
    Prev
    Next
    INDEX
    Explanations

    tapestry of woven

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_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
    exion
    2.10
    Germain
    2.08
    ころ
    2.05
    蒼
    2.03
    batas
    1.96
    scopic
    1.90
    Ĝ
    1.87
    depth
    1.86
     prič
    1.86
    errors
    1.84
    POSITIVE LOGITS
    ت
    1.51
    ingi
    1.50
    itational
    1.48
    ing
    1.45
    ingan
    1.39
    inga
    1.38
    xsi
    1.37
    strconv
    1.36
    تمل
    1.32
    veh
    1.32
    Activations Density 0.176%

    No Known Activations