© 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. 22136
    Prev
    Next
    INDEX
    Explanations

    paired β-sheets, an emerald

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

    structural elements and specific contexts

    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
     rebate
    0.49
     ▶
    0.47
    𝙢
    0.46
     verg
    0.46
    一
    0.46
     derivative
    0.45
    ቆዳ
    0.45
    一颗
    0.45
     డి
    0.44
     peces
    0.44
    POSITIVE LOGITS
     Wh
    0.54
    in
    0.50
    Wh
    0.49
     Passage
    0.48
     Antique
    0.47
    i
    0.47
     Emer
    0.47
     অনুমান
    0.47
     Ancient
    0.46
     Union
    0.46
    Activations Density 0.000%

    No Known Activations