© 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. 128590
    Prev
    Next
    INDEX
    Explanations

    About "About"

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

    designing, student, Chen, generation

    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
     tatha
    0.57
     eder
    0.53
     Tron
    0.51
     杨
    0.51
     избран
    0.50
     dźwię
    0.50
     Verme
    0.50
     Ashken
    0.49
     เสียง
    0.49
     initials
    0.47
    POSITIVE LOGITS
    페
    0.48
    ná
    0.48
    餅
    0.48
    로
    0.47
    t
    0.46
    Port
    0.45
    Fetch
    0.45
    spedes
    0.45
    म
    0.45
    Serve
    0.42
    Activations Density 0.000%

    No Known Activations