© 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. 37071
    Prev
    Next
    INDEX
    Explanations

    ultimately aid boost income

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

    legal, technical, and marketing terms

    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
    ’
    0.57
     I
    0.53
    onin
    0.50
     Brown
    0.48
     pressed
    0.47
    აძ
    0.47
    arly
    0.46
     s
    0.46
     Principle
    0.46
     Porter
    0.45
    POSITIVE LOGITS
     वगैर
    0.55
    程度上
    0.55
     वगैरह
    0.54
    GALAD
    0.52
    功率
    0.52
    િવસ
    0.50
     বিক্রয়
    0.49
    演绎
    0.49
    खेल
    0.48
     ત્યાર
    0.47
    Activations Density 0.000%

    No Known Activations