© 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. 44373
    Prev
    Next
    INDEX
    Explanations

    holy months, recorded, use your

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

    information, winter, happy, nutrition, present

    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
     dynasties
    0.38
     Richmond
    0.37
     мүмкүн
    0.37
     나머
    0.36
     Riley
    0.36
     Mosca
    0.35
    <h3>
    0.35
     什么
    0.35
     эмо
    0.35
     удар
    0.35
    POSITIVE LOGITS
    क्षेत्र
    0.44
    グルメ
    0.42
    milk
    0.40
    Seine
    0.40
    available
    0.39
     använd
    0.38
    extra
    0.38
    professional
    0.38
    pearl
    0.38
    profile
    0.37
    Activations Density 0.000%

    No Known Activations