© 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. 39749
    Prev
    Next
    INDEX
    Explanations

    the technical, importance of

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

    Latest work from OpenAI

    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
    {|
    0.45
    本项目
    0.45
    ли
    0.43
    বঙ্গ
    0.43
    литься
    0.42
     खिला
    0.42
    Buzz
    0.42
    碧
    0.41
    
    0.41
    给人
    0.40
    POSITIVE LOGITS
    وامی
    0.51
    dzie
    0.50
     중국
    0.49
    avad
    0.49
    AGMENT
    0.48
     mês
    0.48
     oksid
    0.47
     extranjeros
    0.47
     müs
    0.46
     rezat
    0.46
    Activations Density 0.000%

    No Known Activations