© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 2287
    Prev
    Next
    INDEX
    Explanations

    time with am or pm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_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
    ◼
    0.74
     $(<
    0.74
     neglig
    0.74
     quadrature
    0.72
    efeu
    0.72
    örer
    0.70
     finite
    0.70
     (>
    0.70
     operands
    0.70
     flavonoid
    0.68
    POSITIVE LOGITS
    pm
    2.64
     pm
    2.60
    PM
    2.53
     PM
    2.51
    Pm
    1.89
    AM
    1.75
     Pm
    1.74
     AM
    1.69
     पीएम
    1.66
     am
    1.62
    Activations Density 0.157%

    No Known Activations