© 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. 208899
    Prev
    Next
    INDEX
    Explanations

    house making

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

    provides comic relief

    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
     silencing
    0.48
     silice
    0.46
     Gaye
    0.45
     relocate
    0.45
    <0xBF>
    0.44
     teint
    0.44
     supprimer
    0.44
     collabor
    0.44
     paleont
    0.44
     Lor
    0.44
    POSITIVE LOGITS
     الش
    0.49
    الش
    0.47
     मनी
    0.47
     وتق
    0.46
    လက်
    0.46
    ال
    0.45
    ta
    0.44
     زده
    0.43
    ts
    0.43
    魷
    0.43
    Activations Density 0.000%

    No Known Activations