© 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. 16-GEMMASCOPE-2-RES-262K
    7. 42622
    Prev
    Next
    INDEX
    Explanations

    Harley Quinn, quantum groups, antimuscarinic

    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_16_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
    ’
    0.71
    পশ্চিম
    0.64
    অন
    0.63
    も
    0.62
    コン
    0.61
    エン
    0.61
    シ
    0.60
     لي
    0.59
    サイズ
    0.58
    ليه
    0.57
    POSITIVE LOGITS
     Aztec
    0.63
     anthracene
    0.61
     omnichannel
    0.61
     anthocyan
    0.60
     intrad
    0.58
     calculi
    0.56
     degenerative
    0.56
     disson
    0.56
    minton
    0.55
     twinning
    0.55
    Activations Density 0.001%

    No Known Activations