© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 228627
    Prev
    Next
    INDEX
    Explanations

    modern design ideas

    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
     half
    0.47
     folded
    0.45
     surroundings
    0.44
    u
    0.44
     tasks
    0.44
     pair
    0.43
     focused
    0.43
     dotted
    0.43
     СК
    0.43
     offen
    0.42
    POSITIVE LOGITS
     كتب
    0.52
    থি
    0.52
     سوق
    0.52
     اصحاب
    0.51
    }^{(
    0.50
     يص
    0.50
    بير
    0.49
    躹
    0.49
     جمه
    0.49
    ទទួល
    0.49
    Activations Density 0.001%

    No Known Activations