© 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. 154527
    Prev
    Next
    INDEX
    Explanations

    mobile app

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

    potential impact on society

    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
    𝒗
    0.49
    幷
    0.49
    dengan
    0.49
    ﻊ
    0.49
    DH
    0.48
    лі
    0.48
     приветствовать
    0.48
    FIGURE
    0.48
    ﺪ
    0.47
    
    0.47
    POSITIVE LOGITS
     output
    0.58
     their
    0.56
     discs
    0.55
     accuracy
    0.55
     workshops
    0.54
     ancestors
    0.54
     embassies
    0.54
     customers
    0.53
     families
    0.53
     unsafe
    0.53
    Activations Density 0.001%

    No Known Activations