© 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. 197833
    Prev
    Next
    INDEX
    Explanations

    references or products

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

    introducing contrast

    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
    ளவில்
    0.54
    Parameteri
    0.48
     сложно
    0.46
    ભાવ
    0.46
    码
    0.45
    理性
    0.45
    駕
    0.45
    XmlElement
    0.44
     جوجل
    0.44
    どんどん
    0.43
    POSITIVE LOGITS
    s
    0.66
    fpr
    0.57
     ll
    0.55
     (=
    0.53
    protein
    0.51
    in
    0.50
     LL
    0.49
    রাষ্ট্রমন্ত্রী
    0.49
     Jl
    0.49
     prior
    0.49
    Activations Density 0.001%

    No Known Activations