© 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-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 165706
    Prev
    Next
    INDEX
    Explanations

    public, foreign, and technical language

    np_acts-logits-general · gemini-2.5-flash-lite

    mobile, vibrant, families, coconut, yellow

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    ټ
    0.59
    িশ
    0.49
    い
    0.48
    量の
    0.47
    __
    0.45
    蟀
    0.45
    .=
    0.44
    .~
    0.43
    through
    0.43
    گل
    0.43
    POSITIVE LOGITS
     发布
    0.53
     सुरक्षा
    0.49
     accomp
    0.48
     חלק
    0.45
     สะ
    0.45
     publik
    0.44
     包括
    0.44
     TV
    0.44
    pyridazin
    0.44
     zakon
    0.44
    Activations Density 0.000%

    No Known Activations