© 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. 183761
    Prev
    Next
    INDEX
    Explanations

    actions and states

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

    discover machine learning algorithms

    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
     숙
    0.48
     ${
    0.47
     Email
    0.47
     class
    0.47
    bergen
    0.46
     Class
    0.45
     Table
    0.45
     harboring
    0.45
     $_{
    0.45
     Serve
    0.44
    POSITIVE LOGITS
    登山
    0.48
     estimations
    0.46
    ὺ
    0.44
    ουν
    0.44
    ám
    0.43
     declaró
    0.42
     aislado
    0.42
     নিতান্ত
    0.41
    Compar
    0.41
     demuestra
    0.41
    Activations Density 0.000%

    No Known Activations