© 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. 172868
    Prev
    Next
    INDEX
    Explanations

    material and opinion

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

    representations, concerns, not, locally

    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
    レンズ
    0.54
    亞
    0.53
     funkce
    0.49
    鈑
    0.49
    ф
    0.46
    ਮ
    0.46
     sélectionnés
    0.46
    ফোন
    0.46
     rallied
    0.45
     それぞれ
    0.45
    POSITIVE LOGITS
     ISZ
    0.46
     नाइ
    0.44
     गुण
    0.44
    )^{-
    0.43
     Garlic
    0.43
    ail
    0.41
     الشع
    0.40
    jia
    0.40
     gamma
    0.39
     stupid
    0.39
    Activations Density 0.002%

    No Known Activations