© 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. 29506
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers

    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
    倸
    0.45
    鏝
    0.45
    จึง
    0.45
     प्रकल्
    0.44
    टर
    0.43
    กำลัง
    0.43
    ೋಗ
    0.42
    央
    0.42
    弋
    0.42
    ทรง
    0.42
    POSITIVE LOGITS
     How
    0.57
     more
    0.55
     what
    0.55
     much
    0.54
     What
    0.53
     how
    0.53
     lo
    0.51
     ironically
    0.50
     straight
    0.49
     heroes
    0.49
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.