© 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. 95764
    Prev
    Next
    INDEX
    Explanations

    representation or alternatives

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

    academic and social topics

    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
    谍
    0.52
    Number
    0.52
     बॉर्डर
    0.51
     шести
    0.49
     दीक्षित
    0.48
     प्रमेय
    0.48
     डबल
    0.46
    筛
    0.46
     કરોડ
    0.46
     בש
    0.45
    POSITIVE LOGITS
     và
    0.47
    不懂
    0.45
     و
    0.45
     tên
    0.44
    στη
    0.44
    ){}
    0.44
     TOUR
    0.43
     deber
    0.43
     descon
    0.42
     TASK
    0.42
    Activations Density 0.000%

    No Known Activations