© 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. 249226
    Prev
    Next
    INDEX
    Explanations

    you can use

    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
    তল
    0.59
     ufficial
    0.54
    いますが
    0.53
    フェ
    0.51
    ্ট
    0.49
    タ
    0.49
     प्रतिरक्षा
    0.48
    ইংরেজি
    0.47
    來自
    0.46
    サイズ
    0.46
    POSITIVE LOGITS
     precipitates
    0.49
     dimers
    0.48
    Pw
    0.45
     spheres
    0.45
    Histor
    0.44
     Богу
    0.44
     Θ
    0.44
     doodles
    0.43
    ogens
    0.42
     다양
    0.42
    Activations Density 0.002%

    No Known Activations