© 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. 78346
    Prev
    Next
    INDEX
    Explanations

    contribution to

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

    friendship, watching, analysis, technical 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
     Coppola
    0.44
     Dey
    0.43
     Patty
    0.43
    据
    0.42
     воору
    0.42
     Alina
    0.42
     Coy
    0.42
    投手
    0.41
     Rousse
    0.41
     Matsumoto
    0.41
    POSITIVE LOGITS
    ار
    0.48
     অবদান
    0.47
    ید
    0.46
     চাইলে
    0.46
     انواع
    0.46
    اید
    0.45
    ژ
    0.45
    وبی
    0.45
    اہ
    0.44
     اضافه
    0.44
    Activations Density 0.002%

    No Known Activations