© 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. 27798
    Prev
    Next
    INDEX
    Explanations

    mathematical fractions and dates

    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
    כון
    0.42
     correspondences
    0.40
     constituents
    0.40
     correspondence
    0.40
    p
    0.39
    ppro
    0.39
    ष्य
    0.38
    igui
    0.38
    सीएस
    0.38
    블
    0.38
    POSITIVE LOGITS
     dinast
    0.47
     неста
    0.46
     concepto
    0.45
     violência
    0.45
     complejo
    0.45
     пера
    0.45
     காற்ற
    0.44
     نسم
    0.44
     трав
    0.44
     ''){
    0.44
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.