© 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. 138380
    Prev
    Next
    INDEX
    Explanations

    describing and listing objects/sections

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

    specific terms and concepts

    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
    ლები
    0.44
     マイ
    0.43
     salespeople
    0.42
    ほとんど
    0.41
     presque
    0.41
    পাশের
    0.40
    不會
    0.39
    🤷
    0.39
     wouldn
    0.39
    ഫോ
    0.38
    POSITIVE LOGITS
     столь
    0.46
     venerable
    0.45
     fascinating
    0.45
     کئے
    0.44
     intriguing
    0.43
     ingenious
    0.43
     весьма
    0.43
     wondrous
    0.43
     vitally
    0.42
     thrilling
    0.42
    Activations Density 0.007%

    No Known Activations