© 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. 117314
    Prev
    Next
    INDEX
    Explanations

    furniture, housing, distribution, notice

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

    changed, formally, allow

    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
     splic
    0.47
     améli
    0.46
    眼前
    0.45
     timeout
    0.44
     paralle
    0.44
     entire
    0.43
    ItemLayout
    0.43
     I
    0.43
    어를
    0.43
     absoluto
    0.43
    POSITIVE LOGITS
     назна
    0.57
     назначения
    0.52
    छ
    0.51
     furnish
    0.49
    furn
    0.48
    Topics
    0.47
    Furn
    0.46
    তেই
    0.46
    genommen
    0.45
    ⚛
    0.44
    Activations Density 0.001%

    No Known Activations