© 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. 49246
    Prev
    Next
    INDEX
    Explanations

    Happy, manage, access, collection

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

    implementation benefits

    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
    地产
    0.50
    Rename
    0.46
    云
    0.46
     Color
    0.46
    星期
    0.45
    Chiều
    0.45
    Picture
    0.44
     Pizza
    0.44
    艺
    0.44
     Actors
    0.43
    POSITIVE LOGITS
     oblivious
    0.55
     pantallas
    0.49
     manos
    0.48
     ඔබේ
    0.48
     feit
    0.48
     DWI
    0.47
    ailed
    0.47
     giurid
    0.47
     nier
    0.47
     inap
    0.47
    Activations Density 0.000%

    No Known Activations