© 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. 573
    Prev
    Next
    INDEX
    Explanations

    way, convenient, positive

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

    suggestions and what you can do

    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
    試料
    0.51
    目が
    0.48
     respaldo
    0.46
     ಗು
    0.45
     心
    0.44
    ि
    0.44
    евского
    0.43
    視野
    0.43
     गिनती
    0.43
    襯
    0.43
    POSITIVE LOGITS
     možete
    0.60
     můžete
    0.51
    ക്കാം
    0.48
     môžete
    0.48
     uključ
    0.47
     ৬৮
    0.46
    łości
    0.45
    mıştır
    0.45
     uop
    0.45
    ěl
    0.44
    Activations Density 0.000%

    No Known Activations