© 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. 40-GEMMASCOPE-2-RES-262K
    7. 132259
    Prev
    Next
    INDEX
    Explanations

    class names and attributes

    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_40_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
     `--
    0.41
    nextDouble
    0.40
    êter
    0.40
    মিত
    0.40
     Undergraduate
    0.39
    Triangle
    0.38
    ड्रा
    0.38
    ၜ
    0.37
    pidos
    0.36
    娣
    0.36
    POSITIVE LOGITS
     kelas
    0.51
     klasse
    0.45
     class
    0.39
     noir
    0.39
    ्युन
    0.39
    InputValue
    0.38
     supre
    0.38
     Klasse
    0.38
     dure
    0.38
     Kelas
    0.38
    Activations Density 0.002%

    No Known Activations