© 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. 173322
    Prev
    Next
    INDEX
    Explanations

    HTML tags: i, button

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

    HTML classes and elements

    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
    হইয়া
    0.48
    șit
    0.47
    ">–
    0.47
    hatiti
    0.47
    ExternalTaskPojo
    0.46
     zespołu
    0.46
     صلى
    0.46
     yellowish
    0.45
    ḓ
    0.45
     grayish
    0.45
    POSITIVE LOGITS
    週間
    0.41
     T
    0.40
     Bruder
    0.39
     전국
    0.38
    各大
    0.38
    stdio
    0.37
    avio
    0.37
     டி
    0.37
    <0xE2>
    0.37
    受信
    0.36
    Activations Density 0.000%

    No Known Activations