© 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. 61491
    Prev
    Next
    INDEX
    Explanations

    stud earrings, many illegitimate

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

    section beginnings and introductions

    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
     显示
    0.60
     〢
    0.55
     吃
    0.52
     或者
    0.47
     类型
    0.47
     东
    0.47
     含
    0.47
    髹
    0.47
     從
    0.46
     文件
    0.45
    POSITIVE LOGITS
     بیک
    0.46
     sesión
    0.44
    credentials
    0.43
     стороны
    0.42
     nale
    0.42
     mendengar
    0.42
    ずれ
    0.42
     slimming
    0.42
     enjoyable
    0.42
    왁
    0.42
    Activations Density 0.000%

    No Known Activations