© 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. 89142
    Prev
    Next
    INDEX
    Explanations

    place before

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

    hardware accessibility

    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
    <unused277>
    0.53
     bhfu
    0.51
    ifiques
    0.50
    <unused433>
    0.50
     carinatis
    0.49
    anhyd
    0.49
    Unsupported
    0.48
    ⚤
    0.48
     tarses
    0.48
    <unused1764>
    0.48
    POSITIVE LOGITS
    当然
    0.48
    ку
    0.47
    辕
    0.45
    はもちろん
    0.43
     Data
    0.43
    两个
    0.42
     control
    0.41
    《
    0.41
     Spectra
    0.40
     ముఖ్య
    0.40
    Activations Density 0.001%

    No Known Activations