© 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. 72413
    Prev
    Next
    INDEX
    Explanations

    http followed by ://

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

    string literal "Hello, world!"

    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
    </h1>
    0.57
    </h2>
    0.55
    </h3>
    0.54
    </h5>
    0.52
     Emission
    0.46
     Describes
    0.46
     Interaction
    0.45
    </blockquote>
    0.45
     Kalk
    0.45
    </h6>
    0.45
    POSITIVE LOGITS
    akiem
    0.59
     सरिया
    0.54
    igel
    0.50
     यू
    0.49
    StarGo
    0.49
    adona
    0.49
     አንዳንድ
    0.49
    受欢迎
    0.49
    amalla
    0.48
    aków
    0.48
    Activations Density 0.000%

    No Known Activations