© 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. 114601
    Prev
    Next
    INDEX
    Explanations

    Volume or location details

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

    legal frameworks

    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
    س
    0.49
     milkshake
    0.47
    ضه
    0.47
     précédemment
    0.46
    是将
    0.46
     replacements
    0.46
     smears
    0.46
     matchs
    0.45
     vez
    0.44
     inserts
    0.44
    POSITIVE LOGITS
     हेक्टेयर
    0.48
     ג
    0.47
     описа
    0.47
     על
    0.46
    Chapters
    0.46
     ጥ
    0.46
    Jangan
    0.46
    Listeners
    0.46
    LineWidth
    0.45
    Titulo
    0.45
    Activations Density 0.002%

    No Known Activations