© 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. 61076
    Prev
    Next
    INDEX
    Explanations

    found this, pursuant to, saving money

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

    legal interpretation case

    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
    ü
    0.61
    k
    0.50
     eine
    0.50
     werden
    0.48
    ene
    0.46
     förm
    0.45
    nění
    0.45
    m
    0.45
     ismer
    0.45
     intoxication
    0.44
    POSITIVE LOGITS
     постави
    0.52
    ಗ
    0.51
    orescent
    0.49
     мяс
    0.48
     ಗ
    0.46
     муж
    0.46
     слова
    0.45
     교회
    0.44
     ஈடுபட்டு
    0.44
     ಹೃ
    0.44
    Activations Density 0.001%

    No Known Activations