© 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. 127277
    Prev
    Next
    INDEX
    Explanations

    conjunctions and descriptions

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

    opportunities and risks

    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
    sentiment
    0.43
    ح
    0.41
    loading
    0.41
     गवर्नमेंट
    0.40
     roundabout
    0.39
    га
    0.39
     मुद्दे
    0.39
     महार
    0.38
    Wah
    0.38
    تف
    0.38
    POSITIVE LOGITS
     மற்றும்
    0.52
     ಹಾಗೂ
    0.51
     oraz
    0.50
     和
    0.50
     envers
    0.49
     レ
    0.48
     그리고
    0.48
     sparsim
    0.48
     وحتى
    0.48
    walten
    0.48
    Activations Density 0.000%

    No Known Activations