© 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. 161428
    Prev
    Next
    INDEX
    Explanations

    elegance gift based look portal lot running

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

    adaptive learning platforms

    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
    uaje
    0.50
    利用
    0.50
    用
    0.48
    入
    0.47
     utilizes
    0.46
    ριά
    0.46
     utilised
    0.45
    用于
    0.45
    魁
    0.44
     polémica
    0.44
    POSITIVE LOGITS
     любовь
    0.49
     Hym
    0.49
     스타
    0.49
    <unused582>
    0.47
     Kishan
    0.47
     vah
    0.47
    ಂಕ
    0.46
    !</
    0.46
     আসল
    0.46
     kriminal
    0.46
    Activations Density 0.000%

    No Known Activations