© 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. 251445
    Prev
    Next
    INDEX
    Explanations

    battery

    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
    res
    0.53
    at
    0.49
    as
    0.48
    n
    0.46
     Reprodu
    0.46
     (
    0.44
    hd
    0.43
    s
    0.43
    ps
    0.43
     kter
    0.42
    POSITIVE LOGITS
    腃
    0.53
    🖍
    0.53
    <unused558>
    0.49
     যাত্রী
    0.48
    }{$\
    0.47
    グッズ
    0.46
    
    0.46
    ジム
    0.46
    𝗗
    0.45
    ंबे
    0.45
    Activations Density 0.001%

    No Known Activations