© 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. 195402
    Prev
    Next
    INDEX
    Explanations

    curcumin, disorders, claimed

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

    communication skills, demand, education, structure, programming

    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
     Access
    0.50
    集体
    0.50
    >(
    0.47
     (
    0.46
    0.46
     identifiable
    0.45
     intervention
    0.45
     Skills
    0.44
     [...]
    0.44
     interven
    0.44
    POSITIVE LOGITS
    <unused635>
    0.58
    whale
    0.54
     المحاضره
    0.52
    harga
    0.52
     মূল্য
    0.52
    ávez
    0.51
     Sonne
    0.51
    룔
    0.51
    <unused505>
    0.51
    غي
    0.51
    Activations Density 0.001%

    No Known Activations