© 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. 222002
    Prev
    Next
    INDEX
    Explanations

    professionals lecturing internationally

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

    matplotlib.pyplot code and concepts

    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
     熱
    0.53
     或者
    0.51
     촬영
    0.50
    illerie
    0.50
     北
    0.49
     ভয়াবহ
    0.49
     আশ
    0.49
    ließ
    0.49
     受
    0.49
     着
    0.48
    POSITIVE LOGITS
    沣
    0.50
     we
    0.45
     you
    0.44
    watermelon
    0.44
     участке
    0.43
    ڑی
    0.41
    ۰
    0.41
     Dumping
    0.40
     участок
    0.40
    اوی
    0.40
    Activations Density 0.000%

    No Known Activations