© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 137538
    Prev
    Next
    INDEX
    Explanations

    Presenting, scaling, attention

    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
     aant
    0.35
     sami
    0.33
     sayings
    0.33
     ت
    0.32
    伨
    0.32
     ráp
    0.31
     gals
    0.30
    茶
    0.30
     samot
    0.30
     locations
    0.30
    POSITIVE LOGITS
    NAME
    0.43
    或許
    0.43
     найбіль
    0.42
    1
    0.41
     अगले
    0.40
     помимо
    0.40
     će
    0.40
    {\
    0.39
     бясплат
    0.39
    最初の
    0.38
    Activations Density 0.083%

    No Known Activations