© 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. 51719
    Prev
    Next
    INDEX
    Explanations

    fundamental and absolute concepts

    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
     wichtigsten
    0.45
     controlado
    0.43
    ബ
    0.42
    форм
    0.42
    شا
    0.42
     dozens
    0.42
    最重要的
    0.41
     caoutch
    0.41
     handeln
    0.41
    ﹞
    0.40
    POSITIVE LOGITS
     jiné
    0.49
    某个
    0.44
    eni
    0.44
    ien
    0.42
     organism
    0.42
     polity
    0.42
     persoane
    0.40
    ләре
    0.40
    uire
    0.40
     life
    0.39
    Activations Density 0.021%

    No Known Activations