© 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. 124650
    Prev
    Next
    INDEX
    Explanations

    feather

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

    focusing on specific topics

    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
    üğü
    0.50
    assaytype
    0.50
    猚
    0.50
     fonctionnalités
    0.49
     चाँ
    0.49
    किया
    0.48
    institut
    0.48
    勖
    0.48
     سوش
    0.47
    𝕌
    0.47
    POSITIVE LOGITS
     inspecting
    0.50
    feather
    0.49
     reloading
    0.49
     v
    0.48
     exit
    0.47
     feather
    0.47
     Feather
    0.47
     Edit
    0.46
     fe
    0.45
     feathered
    0.45
    Activations Density 0.001%

    No Known Activations