© 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. 16199
    Prev
    Next
    INDEX
    Explanations

    network provided distinguishing new

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

    but, without, however

    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
     WHICH
    0.46
     управ
    0.43
     која
    0.42
     costumbre
    0.40
    ظ
    0.40
    唖
    0.39
    uestas
    0.39
     unidad
    0.38
    례
    0.38
     کړ
    0.38
    POSITIVE LOGITS
    लेकिन
    0.48
     altre
    0.42
     वैलेंट
    0.41
     other
    0.39
    কিন্তু
    0.39
    วันนี้
    0.39
     但是
    0.38
     ប៉ុ
    0.38
     but
    0.38
     without
    0.38
    Activations Density 0.000%

    No Known Activations