© 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. 136974
    Prev
    Next
    INDEX
    Explanations

    your data

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

    work, money, personal issues

    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
     "
    0.49
     enclave
    0.48
     اللون
    0.48
     dijete
    0.48
     ICI
    0.47
     izgub
    0.46
     untapped
    0.45
    achlor
    0.45
     enam
    0.45
     energia
    0.44
    POSITIVE LOGITS
    璈
    0.50
    oteur
    0.49
    
    0.49
    साईट
    0.49
    एस्ट
    0.47
    Архі
    0.47
    rives
    0.47
    кое
    0.46
    ających
    0.45
    бліоте
    0.45
    Activations Density 0.001%

    No Known Activations