© 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. 32675
    Prev
    Next
    INDEX
    Explanations

    No matter

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

    reasons behind

    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
    䒱
    0.55
    酔
    0.52
    そのまま
    0.50
    মন্ত্র
    0.50
    nomenclature
    0.47
     দূর
    0.47
    รู้
    0.47
    ۪
    0.46
    د
    0.45
    ลอด
    0.45
    POSITIVE LOGITS
    inė
    0.53
    ंख्य
    0.48
     scarf
    0.46
     facial
    0.46
     dresses
    0.45
     scarves
    0.45
     saved
    0.44
    انية
    0.44
     threatening
    0.44
     days
    0.44
    Activations Density 0.000%

    No Known Activations