© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 34652
    Prev
    Next
    INDEX
    Explanations

    currency, time, similarity, cynicism, invalidity

    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
    സ്യ
    0.45
    śmy
    0.43
     articulating
    0.42
    ，“
    0.41
    emain
    0.41
    该
    0.41
     Ph
    0.40
    Actress
    0.40
     Arm
    0.40
    érieur
    0.40
    POSITIVE LOGITS
    MAPb
    0.52
    caches
    0.47
     franqu
    0.47
    _='
    0.44
     offshoring
    0.43
     liberd
    0.43
     cq
    0.43
     pec
    0.43
     pecan
    0.43
     caiu
    0.42
    Activations Density 0.001%

    No Known Activations