© 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. 31-GEMMASCOPE-2-RES-262K
    7. 78979
    Prev
    Next
    INDEX
    Explanations

    transactions and inventories

    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
    adiya
    0.47
    。
    0.45
    س
    0.44
     случаев
    0.44
    łe
    0.43
    .).
    0.42
    慗
    0.42
     તે
    0.41
    ujące
    0.41
    ajte
    0.40
    POSITIVE LOGITS
     inventories
    0.53
     furnished
    0.46
     furnish
    0.46
     OFFER
    0.45
     inventory
    0.44
     furnishes
    0.44
     infant
    0.43
    furnished
    0.42
     reliable
    0.42
     elections
    0.42
    Activations Density 0.017%

    No Known Activations