© 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. 88017
    Prev
    Next
    INDEX
    Explanations

    visual representations

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

    actors, dialogue, statements, constructor

    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
    不仅
    0.46
    จริงๆ
    0.44
    ຕະ
    0.44
    ញ្
    0.43
    促销
    0.43
     Shortcut
    0.42
    Shortcut
    0.41
    규
    0.41
    iviato
    0.41
    优惠
    0.41
    POSITIVE LOGITS
     düşün
    0.48
    comedy
    0.47
    ESO
    0.46
     অভিনয়ের
    0.45
     মৃত্যু
    0.45
     পুত্রের
    0.45
     poema
    0.45
     устройство
    0.45
     ordinairement
    0.45
     વિચાર
    0.44
    Activations Density 0.000%

    No Known Activations