© 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. 39805
    Prev
    Next
    INDEX
    Explanations

    company headquarters and foreign languages

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

    colon followed by parentheses or code

    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
     ケ
    0.47
     Precious
    0.47
     Occasionally
    0.46
    urger
    0.45
     undergoing
    0.44
     Lyft
    0.44
     Ow
    0.43
    お子
    0.42
     متعلق
    0.42
     Keto
    0.42
    POSITIVE LOGITS
    ويم
    0.58
     svim
    0.54
    ל
    0.50
    𝖑
    0.49
    लेकिन
    0.48
    ായി
    0.48
    Таким
    0.48
    вят
    0.47
    স্ব
    0.47
    Всім
    0.47
    Activations Density 0.000%

    No Known Activations