© 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. 154594
    Prev
    Next
    INDEX
    Explanations

    companies giving services

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

    practical effects action

    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
    session
    0.55
    saldo
    0.47
    լ
    0.46
    level
    0.45
     ghe
    0.44
    sni
    0.42
     level
    0.41
    দ্দ
    0.41
    type
    0.41
     envisaged
    0.41
    POSITIVE LOGITS
     Whey
    0.47
     <!--<
    0.47
     Technology
    0.46
     strani
    0.46
     Yeast
    0.46
     Calcium
    0.46
     Turns
    0.45
     Dempsey
    0.45
     DEM
    0.44
    обу
    0.44
    Activations Density 0.002%

    No Known Activations