© 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. 159638
    Prev
    Next
    INDEX
    Explanations

    we are, us

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

    energy, physics, and learning

    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
     firearm
    0.47
    ्ट
    0.45
     espèces
    0.45
    hawk
    0.44
    虎
    0.44
     RPC
    0.44
    雪
    0.43
    吉
    0.43
    신
    0.43
    美国
    0.42
    POSITIVE LOGITS
     प्रकाश
    0.53
     conforme
    0.48
     Yani
    0.47
     Como
    0.47
     Sada
    0.47
     दिली
    0.46
     হয়নি
    0.46
     generously
    0.46
     ማለት
    0.46
     நன்ற
    0.45
    Activations Density 0.000%

    No Known Activations