© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 13192
    Prev
    Next
    INDEX
    Explanations

    submitted by

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    лм
    0.74
    них
    0.73
    EtOH
    0.73
    mainWindow
    0.71
    يا
    0.70
    ية
    0.68
    沌
    0.68
    bilical
    0.68
    ние
    0.67
    д
    0.66
    POSITIVE LOGITS
    ed
    0.75
    d
    0.69
     de
    0.68
     le
    0.67
     in
    0.66
     may
    0.64
     stessa
    0.64
     says
    0.64
     community
    0.63
     bent
    0.63
    Activations Density 0.000%

    No Known Activations