© 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. 30475
    Prev
    Next
    INDEX
    Explanations

    themes, stability, Einstein

    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
    Bitcoin
    0.52
    jna
    0.47
     блоки
    0.46
    ན
    0.46
     получить
    0.46
    EMON
    0.45
     направ
    0.44
     tolerate
    0.44
    рованного
    0.44
     инде
    0.43
    POSITIVE LOGITS
    ي
    0.49
     Herc
    0.48
    ా
    0.46
     Harmon
    0.46
     Arts
    0.45
     Fantastic
    0.45
    in
    0.44
     Earth
    0.44
    全新的
    0.43
    ો
    0.43
    Activations Density 0.003%

    No Known Activations