© 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. 46123
    Prev
    Next
    INDEX
    Explanations

    user content and access

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

    fund administration

    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
    Governor
    0.44
    Hid
    0.44
    Sun
    0.43
     губерна
    0.41
     vých
    0.41
    椑
    0.41
    茆
    0.40
     должность
    0.40
    海道
    0.39
    ُونَ
    0.39
    POSITIVE LOGITS
    디
    0.46
     대한민국
    0.41
     bar
    0.38
     제품
    0.38
     가격
    0.37
     디
    0.37
     coronae
    0.37
    डि
    0.36
     검색
    0.36
    딘
    0.36
    Activations Density 0.016%

    No Known Activations