© 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-65K
    7. 55754
    Prev
    Next
    INDEX
    Explanations

    used to drink

    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_65k_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
    ท
    0.56
    А
    0.54
    И
    0.53
    ك
    0.53
    ث
    0.52
    Е
    0.51
    வ
    0.50
    Ба
    0.50
    д
    0.49
    ج
    0.49
    POSITIVE LOGITS
    zetac
    0.52
     identifies
    0.50
     entitles
    0.49
     inhibits
    0.48
     সময়ে
    0.48
     asserts
    0.47
     exhibited
    0.47
     decides
    0.47
     infestations
    0.46
     variants
    0.46
    Activations Density 0.004%

    No Known Activations