© 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. 83364
    Prev
    Next
    INDEX
    Explanations

    food related actions and quantities

    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
     நகா
    0.48
     பொ
    0.48
    hiddenMap
    0.47
    亚博
    0.46
    ൦
    0.45
    涉及
    0.45
    eksiyon
    0.44
    '}}
    0.43
     содержа
    0.43
     conlleva
    0.42
    POSITIVE LOGITS
     ,
    0.53
     if
    0.50
     /
    0.48
     IF
    0.47
     Julian
    0.47
     e
    0.47
     es
    0.46
     hypotension
    0.46
     .
    0.45
     m
    0.45
    Activations Density 0.006%

    No Known Activations