© 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. 100463
    Prev
    Next
    INDEX
    Explanations

    legal or financial arrangements

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

    list items or distinct phrases

    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
    Remove
    0.52
    巡
    0.48
    Swimming
    0.48
    Plant
    0.46
    Animal
    0.46
    Easing
    0.46
    Built
    0.45
    Screw
    0.45
     gewährleisten
    0.45
    Plan
    0.44
    POSITIVE LOGITS
     knuckle
    0.53
    ס
    0.52
     starry
    0.48
     מער
    0.47
     misty
    0.47
     যাহা
    0.46
     চমৎকার
    0.46
     liked
    0.46
     shocking
    0.46
     sketchy
    0.45
    Activations Density 0.001%

    No Known Activations