© 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. 147840
    Prev
    Next
    INDEX
    Explanations

    West kept, firmly planted, a spirit

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

    DDT composition, account holder

    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
    ė
    0.48
    êt
    0.45
    forced
    0.45
    被迫
    0.41
     que
    0.40
    eno
    0.40
    知的
    0.40
    чат
    0.39
     inver
    0.39
     distribu
    0.39
    POSITIVE LOGITS
    apayati
    0.54
    磁盘
    0.51
     NPTypeCode
    0.50
     bilge
    0.49
    🆈
    0.49
     CCc
    0.47
    🆁
    0.47
     renovations
    0.47
    ):\
    0.47
     বেশিরভাগ
    0.46
    Activations Density 0.001%

    No Known Activations