© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 156239
    Prev
    Next
    INDEX
    Explanations

    ergothioneine and djembe

    np_acts-logits-general · gemini-2.5-flash-lite

    legal, damage, violate, demolition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <unused94>
    0.52
     रामानंद
    0.52
     ಸಂಧಿ
    0.52
     भोजन
    0.51
     ış
    0.51
    FullPath
    0.51
    𝓱
    0.51
     레드
    0.51
     extérieur
    0.49
    ຜະລິດຕ
    0.49
    POSITIVE LOGITS
     dissenting
    0.46
    (",
    0.44
     position
    0.44
     anzu
    0.44
    とい
    0.42
    去
    0.42
     sister
    0.41
    nrow
    0.41
     S
    0.41
     n
    0.40
    Activations Density 0.000%

    No Known Activations