© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 199441
    Prev
    Next
    INDEX
    Explanations

    emojis and concepts like diagonally, pressure, quotes

    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_31_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
     γε
    0.46
    贡献
    0.45
    沧
    0.45
     πε
    0.44
     علم
    0.44
     στα
    0.43
     ά
    0.43
    $&$-
    0.41
     Πε
    0.41
    蹄
    0.41
    POSITIVE LOGITS
     menjalani
    0.51
     memiliki
    0.44
     ഇത്തരം
    0.43
    utilisateur
    0.43
    such
    0.42
     performing
    0.42
     이러한
    0.41
    ifon
    0.41
    operasi
    0.41
     such
    0.40
    Activations Density 0.009%

    No Known Activations