© 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. 52183
    Prev
    Next
    INDEX
    Explanations

    technological descriptions or market analysis

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

    simulated simulation requirements

    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
    壇
    0.44
    珽
    0.43
    化粧
    0.42
    亾
    0.42
    帔
    0.41
     pompe
    0.41
    سك
    0.41
     hormone
    0.40
    PRODUCTS
    0.40
    آور
    0.40
    POSITIVE LOGITS
    ':
    0.50
    iling
    0.50
    enarios
    0.50
    fill
    0.48
     isang
    0.46
    adors
    0.46
    for
    0.46
    while
    0.46
    enu
    0.46
    ographics
    0.46
    Activations Density 0.000%

    No Known Activations