© 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. 176031
    Prev
    Next
    INDEX
    Explanations

    Christmas trees

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

    production processes and quality

    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
    jne
    0.45
    朗
    0.43
    懇
    0.43
    而不是
    0.43
    往往
    0.42
    Brandon
    0.41
    フト
    0.40
    ?")
    0.40
    Allan
    0.40
    嘻
    0.40
    POSITIVE LOGITS
     stimmen
    0.52
     poursu
    0.49
     opér
    0.47
     Untersuchung
    0.47
     stimulant
    0.46
    anhyd
    0.46
     തുട
    0.46
     purification
    0.46
     pathophys
    0.45
     चढ़
    0.45
    Activations Density 0.001%

    No Known Activations