© 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. 174563
    Prev
    Next
    INDEX
    Explanations

    science, art, and professional fields

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

    decentralized applications

    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
     chrys
    0.50
     daffodils
    0.49
     อนุ
    0.48
     impurity
    0.47
     adob
    0.47
    ..--..--
    0.46
     jedan
    0.45
     workplaces
    0.45
     alertDialog
    0.45
     церков
    0.45
    POSITIVE LOGITS
    vil
    0.50
    hash
    0.49
    越
    0.49
     Ville
    0.48
    miller
    0.48
    g
    0.47
    uart
    0.47
    жі
    0.47
    et
    0.46
     Kelly
    0.46
    Activations Density 0.000%

    No Known Activations