© 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. 182717
    Prev
    Next
    INDEX
    Explanations

    retail, drawing, band, us, culprits, researchers, catering

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

    describing a state or quality

    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
    January
    0.49
    PERSON
    0.48
    Health
    0.46
    HAR
    0.46
    ADDRESS
    0.46
     Legislative
    0.46
    خ
    0.45
    Topic
    0.45
    Chronic
    0.44
    ىل
    0.44
    POSITIVE LOGITS
     từ
    0.54
     oraș
    0.54
     vecchia
    0.54
     nhà
    0.51
     thúc
    0.51
    蓓
    0.51
     arou
    0.50
     forerunner
    0.50
     Nicky
    0.49
     đế
    0.48
    Activations Density 0.000%

    No Known Activations