© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 28392
    Prev
    Next
    INDEX
    Explanations

    concepts and roles

    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
    -
    0.46
    self
    0.46
     =
    0.45
    ros
    0.44
    :
    0.44
    ’
    0.44
     operated
    0.43
    ran
    0.42
    originally
    0.42
    ake
    0.41
    POSITIVE LOGITS
     ഒരാ
    0.47
     uncanny
    0.47
     horrifying
    0.44
    何况
    0.44
    Acetoxy
    0.43
    ેચ્છ
    0.43
     arguably
    0.42
    DeleteDialogOpen
    0.42
    ᙱ
    0.42
     scarc
    0.42
    Activations Density 0.011%

    No Known Activations