© 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. 14947
    Prev
    Next
    INDEX
    Explanations

    arithmetic operations and expressions

    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
     we
    0.56
    A
    0.56
    I
    0.53
    К
    0.52
     be
    0.51
    J
    0.51
     Call
    0.51
     Me
    0.49
     К
    0.47
     You
    0.47
    POSITIVE LOGITS
     axisymmetric
    0.50
     arithmetic
    0.50
    maxn
    0.49
     outperformed
    0.47
    atsion
    0.46
    Arithmetic
    0.46
    াতিক
    0.46
     neutrophils
    0.46
     jaane
    0.46
     excitatory
    0.45
    Activations Density 0.014%

    No Known Activations