© 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. 131597
    Prev
    Next
    INDEX
    Explanations

    access to

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

    concept art, theory, adrenaline

    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
    কমার্স
    0.47
    ليه
    0.44
    在其
    0.43
    즙
    0.42
    arschijnlijk
    0.41
     بسبب
    0.40
     propose
    0.40
    在我
    0.40
    ኝ
    0.40
    我认为
    0.39
    POSITIVE LOGITS
     explicado
    0.54
    URAL
    0.47
     governs
    0.46
     reinforces
    0.46
    ↵
    0.45
     MANUAL
    0.44
    ｫ
    0.44
     Manual
    0.44
     continuo
    0.43
     financials
    0.42
    Activations Density 0.001%

    No Known Activations