© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 9617
    Prev
    Next
    INDEX
    Explanations

    informations

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

    that is mainly from

    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
    Го
    0.50
    Ге
    0.48
    よね
    0.45
    Бар
    0.45
    Мар
    0.44
    Ш
    0.44
     właśnie
    0.44
     Мар
    0.43
     Kee
    0.43
    ني
    0.43
    POSITIVE LOGITS
     dengan
    0.50
     equipments
    0.50
     ਯ
    0.50
     birçok
    0.47
     sufferings
    0.46
     aantal
    0.46
     with
    0.46
     mnoho
    0.46
     maraming
    0.45
     informations
    0.44
    Activations Density 0.100%

    No Known Activations