© 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. 154615
    Prev
    Next
    INDEX
    Explanations

    industrial, revenues, science, strategy

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

    concepts and ideas

    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
    lis
    0.54
    Fs
    0.52
    im
    0.51
    Properties
    0.48
    os
    0.47
     properties
    0.46
    8
    0.45
     been
    0.45
    %,
    0.45
    Ev
    0.45
    POSITIVE LOGITS
    産業
    0.57
     constituye
    0.55
     اجتماعی
    0.51
     صنعتی
    0.51
     asignatura
    0.50
     அறிவியல்
    0.50
     secteur
    0.50
     inventing
    0.49
     ciencia
    0.48
     ფუნქ
    0.48
    Activations Density 0.000%

    No Known Activations