© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9547
    Prev
    Next
    INDEX
    Explanations

    entity model properties

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

    class definitions in code

    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_40_width_16k_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
    feito
    0.47
    nea
    0.44
    ..!
    0.42
     servlet
    0.42
    !-
    0.42
    embark
    0.40
    vester
    0.40
    paragraph
    0.40
    motif
    0.40
    datat
    0.40
    POSITIVE LOGITS
    Extensions
    0.65
    Properties
    0.62
    Hub
    0.55
    Attributes
    0.54
     Extensions
    0.53
    Models
    0.50
     Properties
    0.49
    𝙴
    0.48
    Profiles
    0.47
    Migrations
    0.46
    Activations Density 0.006%

    No Known Activations