© 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. 73059
    Prev
    Next
    INDEX
    Explanations

    numbers and specific terms

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

    knowledge retrieval internship

    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
     детьми
    0.47
     গোষ্ঠ
    0.47
     идентифика
    0.47
    jezd
    0.47
     вдруг
    0.46
    ﻀ
    0.46
    谨慎
    0.46
     активи
    0.45
     демонстра
    0.45
     தனது
    0.44
    POSITIVE LOGITS
    т
    0.53
    २
    0.52
     softens
    0.51
    ב
    0.51
    t
    0.50
    १
    0.49
     soils
    0.48
    一座
    0.48
     o
    0.47
     softened
    0.47
    Activations Density 0.000%

    No Known Activations