© 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. 130641
    Prev
    Next
    INDEX
    Explanations

    common prepositions and conjunctions

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

    company name

    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
     ފ
    0.48
     શબ્
    0.48
     қи
    0.47
     শব্দটি
    0.47
     轻
    0.47
    öz
    0.46
     semnific
    0.46
     વિ
    0.45
     değiştir
    0.45
    窰
    0.45
    POSITIVE LOGITS
    все
    0.48
    клады
    0.47
    क्ता
    0.47
    𝚗
    0.46
    パ
    0.45
    カタ
    0.45
    الی
    0.45
    мышлен
    0.45
    들어
    0.44
    র্প
    0.44
    Activations Density 0.000%

    No Known Activations