© 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. 244881
    Prev
    Next
    INDEX
    Explanations

    Ming-Chi Kuo, cookies, gene, flights, estuary, parking

    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
    மான
    0.48
    IDENCE
    0.47
    мет
    0.47
    委
    0.46
    薄
    0.45
     trust
    0.45
    滞
    0.45
     worm
    0.44
     transaction
    0.44
     Worm
    0.44
    POSITIVE LOGITS
    rió
    0.56
    ará
    0.56
     बाजू
    0.56
    ra
    0.54
    azzo
    0.54
    𝖺
    0.54
     將
    0.52
     वेगवेगळ्या
    0.52
     வண்ணப்பூ
    0.51
     senjata
    0.51
    Activations Density 0.000%

    No Known Activations