© 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. 51495
    Prev
    Next
    INDEX
    Explanations

    historical archaeology

    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
     amén
    0.50
    神経
    0.49
    テ
    0.48
     obstruct
    0.46
    налу
    0.46
    あ
    0.45
     ந
    0.44
     the
    0.44
    инг
    0.44
     obstructed
    0.44
    POSITIVE LOGITS
    🏭
    0.44
    billing
    0.44
    👿
    0.44
     وصلنا
    0.43
    噤
    0.43
     arsine
    0.42
    ifat
    0.41
    ocide
    0.41
    ASDW
    0.41
     DISNEY
    0.40
    Activations Density 0.004%

    No Known Activations