© 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. 70673
    Prev
    Next
    INDEX
    Explanations

    Christmas presents

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

    terms of endearment and affection

    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
     superar
    0.50
    iters
    0.47
    ophobic
    0.46
    "
    0.46
    osen
    0.45
    rypt
    0.45
    ável
    0.44
    Fig
    0.44
    rs
    0.44
    inas
    0.44
    POSITIVE LOGITS
    лік
    0.50
     racc
    0.47
    อย่างไร
    0.46
    อื่น
    0.45
    ኵ
    0.45
     військо
    0.45
    。“
    0.44
     праців
    0.42
     מער
    0.42
     보이
    0.42
    Activations Density 0.001%

    No Known Activations