© 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. 223848
    Prev
    Next
    INDEX
    Explanations

    specialise in particular procedures

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

    explain complexity and purpose

    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
    kje
    0.47
     حسن
    0.46
    ecd
    0.46
    к
    0.46
    高雄
    0.45
     जुड़े
    0.45
    asyonu
    0.45
     কবি
    0.45
    Κ
    0.44
    kq
    0.44
    POSITIVE LOGITS
     RBIs
    0.43
    漠
    0.42
     посредством
    0.41
     AdWords
    0.41
     UEFA
    0.41
    <unused61>
    0.40
     Wanted
    0.40
     UHS
    0.39
    <0x0B>
    0.39
     Eins
    0.39
    Activations Density 0.001%

    No Known Activations