© 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. 138831
    Prev
    Next
    INDEX
    Explanations

    supports, ruler, father, bedroom

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

    pretends

    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
     अकेले
    0.49
    無線
    0.45
    мок
    0.45
     úpl
    0.45
    ELINE
    0.45
    🫧
    0.44
    فين
    0.43
    交互
    0.43
    灣
    0.43
    ڳ
    0.42
    POSITIVE LOGITS
     appe
    0.46
     abol
    0.46
     demol
    0.46
    కాలు
    0.45
     คง
    0.45
     invers
    0.44
     scat
    0.44
     sulla
    0.44
     investimento
    0.44
     inwest
    0.43
    Activations Density 0.001%

    No Known Activations