© 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. 139245
    Prev
    Next
    INDEX
    Explanations

    search, find, activities, business

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

    irrelevant certainfuels myAI isn'tlightning isn'trise is

    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
    ti
    0.56
    e
    0.55
    t
    0.53
    et
    0.49
    ld
    0.48
    ir
    0.47
    äub
    0.47
    ta
    0.46
    aber
    0.46
    o
    0.46
    POSITIVE LOGITS
    飏
    0.56
     бушлай
    0.53
     ragazzo
    0.53
     scrittura
    0.49
     scoprire
    0.48
     প্রতিক্রিয়া
    0.48
     ইলেক্ট্রোলাই
    0.48
     তারই
    0.47
     repurposed
    0.47
     macchina
    0.47
    Activations Density 0.000%

    No Known Activations