© 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. 164117
    Prev
    Next
    INDEX
    Explanations

    foreign languages and terms

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

    We would like to request

    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
    镙
    0.48
    ängen
    0.47
    完成后
    0.47
    ีด
    0.46
    ʚ
    0.46
    洍
    0.46
    蝎
    0.46
    ից
    0.45
     समापन
    0.45
    بیر
    0.44
    POSITIVE LOGITS
     Of
    0.58
     autochtones
    0.57
     intensely
    0.51
    </h3>
    0.50
     впечат
    0.50
     aconte
    0.50
     mesmer
    0.50
     lengua
    0.48
     impres
    0.48
     electr
    0.48
    Activations Density 0.000%

    No Known Activations