© 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. 217316
    Prev
    Next
    INDEX
    Explanations

    costume, citizens, house, member, dialogues

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

    while contrasting information

    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
    вр
    0.53
    er
    0.52
    粆
    0.49
    掺
    0.45
    ∈</
    0.45
    нд
    0.45
    rable
    0.45
    总量
    0.45
    rende
    0.44
    AdType
    0.44
    POSITIVE LOGITS
    駙
    0.49
     Ona
    0.48
    ೀನ
    0.43
     Holland
    0.41
    চাঁ
    0.41
     Niederlande
    0.41
     ಹೊಂದ
    0.40
     perlu
    0.40
     ona
    0.40
    ']),
    0.40
    Activations Density 0.001%

    No Known Activations