© 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. 164097
    Prev
    Next
    INDEX
    Explanations

    history navigation

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

    Write-Host or computer commands

    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
     निवासी
    0.54
     subiect
    0.45
    ཎ
    0.45
    न्
    0.43
     закон
    0.42
     RAY
    0.42
     prípade
    0.42
    ư
    0.42
    जेदार
    0.41
    Raymond
    0.41
    POSITIVE LOGITS
     Hair
    0.55
     hver
    0.47
     Examination
    0.47
     h
    0.47
     gikk
    0.46
     examinations
    0.46
     Etr
    0.46
     hair
    0.45
     Baill
    0.45
    臀
    0.45
    Activations Density 0.001%

    No Known Activations