© 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. 97270
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and variables

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

    algebraic equations with x

    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
     elef
    0.45
     goose
    0.43
     molecular
    0.40
    ר
    0.39
     কংগ্রেস
    0.39
     camel
    0.38
     grosseur
    0.38
     cooked
    0.38
     condizione
    0.38
    ګ
    0.38
    POSITIVE LOGITS
    ódulo
    0.45
    ousal
    0.44
     Easier
    0.43
    閎
    0.42
     Plast
    0.42
     Vect
    0.42
    क्लेव
    0.42
    节能
    0.41
    ինչ
    0.41
     Séance
    0.41
    Activations Density 0.000%

    No Known Activations