© 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. 70592
    Prev
    Next
    INDEX
    Explanations

    questions and queries

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

    mixed language components

    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
     automotive
    0.42
     performance
    0.42
     employee
    0.41
     entirely
    0.41
    び
    0.41
     ně
    0.41
     sharply
    0.41
     choke
    0.41
     hotly
    0.41
     award
    0.40
    POSITIVE LOGITS
    Những
    0.48
    ủng
    0.47
    १
    0.46
    ૧
    0.46
    Các
    0.45
    عات
    0.44
    Thay
    0.44
    atched
    0.43
    鸾
    0.43
     матри
    0.42
    Activations Density 0.000%

    No Known Activations