© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 22948
    Prev
    Next
    INDEX
    Explanations

    labor people

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

    fusion research

    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
    िन्न
    0.46
    Present
    0.43
    ">\
    0.43
     candied
    0.41
    ")).
    0.41
    ");//
    0.41
    名的
    0.41
     localidad
    0.41
     %@",
    0.41
    ",'
    0.41
    POSITIVE LOGITS
    UFF
    0.45
     Küh
    0.43
     غال
    0.43
     பல்கலைக்கழக
    0.43
     oftentimes
    0.43
    प्रकाश
    0.43
     vaak
    0.43
    daughter
    0.42
     کپ
    0.42
     nonfiction
    0.42
    Activations Density 0.000%

    No Known Activations