© 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-65K
    7. 73
    Prev
    Next
    INDEX
    Explanations

    estimating numerical values

    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_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
    ’
    0.26
     Referring
    0.25
     Expense
    0.23
    ivables
    0.22
     NÃO
    0.22
    '
    0.22
     Supported
    0.22
     Regarding
    0.22
     جنس
    0.21
     (=
    0.21
    POSITIVE LOGITS
     six
    0.61
     approximately
    0.61
     seven
    0.61
     eight
    0.59
     four
    0.58
     roughly
    0.56
     three
    0.55
     five
    0.55
     सुमारे
    0.55
     upwards
    0.54
    Activations Density 1.314%

    No Known Activations