© 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. 173383
    Prev
    Next
    INDEX
    Explanations

    demand

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

    descriptive phrases after verbs

    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
     পিঁপড়া
    0.47
    parser
    0.46
    erode
    0.46
     включа
    0.46
    acotta
    0.46
    存档备份
    0.45
    陆续
    0.45
    鹊
    0.45
    轮回
    0.45
    erà
    0.45
    POSITIVE LOGITS
     demand
    0.46
     cabo
    0.45
    な
    0.44
     عالی
    0.43
     pedi
    0.43
    レンチ
    0.42
    ci
    0.42
     Clients
    0.41
    Demand
    0.40
     DESC
    0.40
    Activations Density 0.001%

    No Known Activations