© 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. 120765
    Prev
    Next
    INDEX
    Explanations

    criterion-referenced tests

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

    enjoying pizza

    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
     accredited
    0.55
     acquired
    0.50
     installed
    0.48
     $
    0.47
     six
    0.47
     build
    0.46
     shortly
    0.45
     first
    0.44
     floor
    0.44
     renewed
    0.44
    POSITIVE LOGITS
     روایت
    0.56
    Woman
    0.50
     엄마
    0.49
    Mama
    0.48
    頩
    0.47
    REAT
    0.47
    Relatives
    0.47
    轵
    0.47
     અને
    0.46
    RESPOND
    0.46
    Activations Density 0.003%

    No Known Activations