© 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. 165712
    Prev
    Next
    INDEX
    Explanations

    US state abbreviations followed by comma

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

    avoiding

    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
     hrs
    0.47
     ഹ
    0.46
    लिसा
    0.46
     حصل
    0.45
     حس
    0.45
    H
    0.45
     coba
    0.45
    َم
    0.44
    Hd
    0.44
     hd
    0.43
    POSITIVE LOGITS
    erent
    0.49
    🍝
    0.49
    ifer
    0.48
    right
    0.47
    lavery
    0.46
    ático
    0.45
    u
    0.43
    蒻
    0.43
    ིས་
    0.43
     leggi
    0.42
    Activations Density 0.000%

    No Known Activations