© 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. 47516
    Prev
    Next
    INDEX
    Explanations

    automatic updates and software features

    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
     apartado
    0.43
    या
    0.42
    з
    0.42
    ப்படவில்லை
    0.41
    ජ
    0.41
     imágenes
    0.40
    ión
    0.39
    මුත්
    0.39
    عکس
    0.39
    자
    0.39
    POSITIVE LOGITS
     Barbar
    0.45
     aneur
    0.44
     Automatic
    0.43
    rectionType
    0.42
     あ
    0.41
     automatic
    0.41
     Chocolate
    0.40
    Automatic
    0.40
     createApp
    0.40
     kors
    0.40
    Activations Density 0.038%

    No Known Activations