© 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. 77809
    Prev
    Next
    INDEX
    Explanations

    you ASAP

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

    launching armed, want more, depicted blue

    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
    ()}.
    0.48
    䙲
    0.47
    નિ
    0.46
     इंपॉर्ट
    0.46
     તેથી
    0.46
    学术
    0.44
     ہوں۔
    0.44
     محاضرات
    0.44
    䀘
    0.44
     તેની
    0.44
    POSITIVE LOGITS
     —
    0.57
     (
    0.54
     -
    0.53
     --
    0.50
     headquartered
    0.50
     pioneered
    0.50
     adalah
    0.49
    trading
    0.49
     Trading
    0.49
     berbasis
    0.49
    Activations Density 0.001%

    No Known Activations