© 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. 159707
    Prev
    Next
    INDEX
    Explanations

    mobile operating system, concerning slavery, grapes, industry, computing technology

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

    transformation and dystopian themes

    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
    扂
    0.48
    جم
    0.47
    از
    0.46
    ِل
    0.45
    ัคร
    0.45
    ación
    0.44
    enciais
    0.43
    дет
    0.42
     Markers
    0.42
    َت
    0.42
    POSITIVE LOGITS
     jTextField
    0.49
     challenged
    0.48
     chromed
    0.48
     விய
    0.46
     JHEP
    0.46
     ቀን
    0.46
     cikin
    0.46
     bloated
    0.46
     န
    0.46
     пут
    0.45
    Activations Density 0.000%

    No Known Activations