© 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. 200901
    Prev
    Next
    INDEX
    Explanations

    can followed by noun

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

    societal progress, system itself

    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
    基本
    0.50
    श
    0.50
     Commence
    0.50
    ა
    0.49
    아
    0.48
    াম
    0.48
     Patterns
    0.48
    শ
    0.48
    s
    0.47
    分
    0.47
    POSITIVE LOGITS
    ır
    0.50
     esperanza
    0.50
     അതു
    0.50
     can
    0.49
     அருகில்
    0.49
     சுவர்
    0.49
     desigualdad
    0.49
    vertebr
    0.48
    кор
    0.48
     නිර්
    0.48
    Activations Density 0.001%

    No Known Activations