© 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. 52627
    Prev
    Next
    INDEX
    Explanations

    explaining ideas and registering actions

    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
     darling
    0.46
     fraudsters
    0.46
     aftermarket
    0.46
    ))]
    0.45
     heavyweight
    0.45
    itelji
    0.45
     shilling
    0.45
    ))
    0.44
     alveolar
    0.43
     wholesalers
    0.43
    POSITIVE LOGITS
     Архи
    0.44
     Парт
    0.43
     Repert
    0.42
     VARIABLES
    0.42
     Physically
    0.41
    澼
    0.41
    வரு
    0.41
     Nature
    0.40
     PLANE
    0.40
     Primer
    0.40
    Activations Density 0.004%

    No Known Activations