© 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. 125050
    Prev
    Next
    INDEX
    Explanations

    maker aryeman, differentiate

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

    medical terms, thinking, and foreign words

    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
     cercando
    0.50
     razvoja
    0.50
     offsets
    0.49
     algunas
    0.47
     BRAND
    0.47
     yanında
    0.46
     towards
    0.46
    𐰺
    0.46
     offsetting
    0.46
    anças
    0.45
    POSITIVE LOGITS
     మాత్ర
    0.51
     hank
    0.46
     बाघ
    0.44
     টাইগার
    0.43
    roje
    0.42
    legg
    0.42
    Drop
    0.41
     जाइए
    0.41
    קט
    0.41
     मेयर
    0.41
    Activations Density 0.000%

    No Known Activations