© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 35908
    Prev
    Next
    INDEX
    Explanations

    US state abbreviations in URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     शहर
    0.47
     Той
    0.47
     (°
    0.47
    ńsk
    0.46
     Фран
    0.46
     mieście
    0.46
     М
    0.45
     İlçesi
    0.44
    郏
    0.44
     ເ
    0.44
    POSITIVE LOGITS
    x
    0.46
    1
    0.41
    2
    0.41
    ERT
    0.38
    وغ
    0.38
    ed
    0.38
    ativen
    0.38
    angement
    0.38
    વારો
    0.36
     interchangeable
    0.36
    Activations Density 0.001%

    No Known Activations