© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 15630
    Prev
    Next
    INDEX
    Explanations

    technical terms and configurations

    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
    ﺴ
    0.42
     conteú
    0.41
     Viceroy
    0.41
     Spani
    0.40
     Redmi
    0.40
    љашње
    0.40
    фесси
    0.40
    LastGen
    0.38
     аутох
    0.38
    स्तक
    0.38
    POSITIVE LOGITS
    י
    0.46
    /-
    0.45
    ской
    0.43
    oretically
    0.43
    рана
    0.41
    _
    0.41
    ي
    0.41
    당
    0.41
    ,
    0.41
    .
    0.40
    Activations Density 0.167%

    No Known Activations