© 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
    2. Gemma-3-270M
    3. 15-GEMMASCOPE-2-RES-16K
    4. 2434
    Prev
    Next
    INDEX
    Explanations

    const declaration or reference

    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_15_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
     ,
    1.74
    ,-
    1.49
     ,
    1.47
     ،
    1.43
    ,__
    1.41
    ,\
    1.38
    ,​
    1.34
     ,[
    1.32
    ,
    1.31
    __,
    1.29
    POSITIVE LOGITS
    слі
    1.85
    ことは
    1.77
    َوْ
    1.76
    sement
    1.75
     seashell
    1.73
     MacBook
    1.72
    liers
    1.71
    以下の
    1.70
     Microscope
    1.70
    langs
    1.69
    Activations Density 0.002%

    No Known Activations