© 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. 136738
    Prev
    Next
    INDEX
    Explanations

    adjective and adjective

    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
    ທີ່ມີ
    0.48
    킨
    0.45
    ーンズ
    0.45
    अर्स
    0.43
     हज़ार
    0.42
    స్కీ
    0.39
    ໃຊ
    0.39
    #,
    0.39
     вычисли
    0.39
    LoopBlend
    0.39
    POSITIVE LOGITS
    पणे
    0.58
     as
    0.56
     indeed
    0.49
    ly
    0.46
    하게
    0.45
     enough
    0.44
    como
    0.44
    Carr
    0.43
     Carr
    0.43
    起來
    0.43
    Activations Density 0.025%

    No Known Activations