© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 209056
    Prev
    Next
    INDEX
    Explanations

    Month of the Military Child

    np_acts-logits-general · gemini-2.5-flash-lite

    smart card history

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     童
    0.58
    జ్య
    0.47
     Laksh
    0.44
     Zombies
    0.44
    班牙
    0.43
     Mikh
    0.43
     symbolName
    0.43
     facilitates
    0.42
     মহাম
    0.42
     مع
    0.41
    POSITIVE LOGITS
     shivering
    0.56
    Nimbus
    0.55
    Rut
    0.49
    ט
    0.48
    Bitter
    0.48
    نیا
    0.47
    𝐶
    0.47
    Ace
    0.47
    Improving
    0.46
    Meth
    0.46
    Activations Density 0.000%

    No Known Activations