© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 4282
    Prev
    Next
    INDEX
    Explanations

    mathematical and programming terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_width_16k_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
    مدة
    2.50
    酵素
    2.50
    عد
    2.47
    رد
    2.46
    onomia
    2.41
     様
    2.40
    比较
    2.39
     религиоз
    2.38
     sociological
    2.37
     distill
    2.37
    POSITIVE LOGITS
     C
    0.98
     X
    0.97
     N
    0.92
     M
    0.88
     A
    0.84
    C
    0.81
     P
    0.81
     S
    0.81
     whose
    0.78
     D
    0.76
    Activations Density 0.085%

    No Known Activations