© 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. 69014
    Prev
    Next
    INDEX
    Explanations

    organizations and roles

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

    thank you or appreciate

    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
     የተለያዩ
    0.57
    רו
    0.50
     주로
    0.50
     ማለት
    0.50
    ро
    0.48
    諡
    0.47
    applications
    0.46
    backgroundImage
    0.45
    ִ
    0.45
    по
    0.45
    POSITIVE LOGITS
    ␥
    0.45
     Audubon
    0.44
     plaus
    0.42
    欵
    0.41
     week
    0.40
     ব্যাপারে
    0.40
    arın
    0.40
     estím
    0.40
     objString
    0.40
     mondo
    0.40
    Activations Density 0.003%

    No Known Activations