© 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. 238054
    Prev
    Next
    INDEX
    Explanations

    definitions of terms

    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
    უბ
    0.52
    廿
    0.52
    鵑
    0.52
     Lobkowicz
    0.52
    municipal
    0.51
    esercizio
    0.51
    реги
    0.50
    έργ
    0.50
    錬
    0.50
    𒅎
    0.50
    POSITIVE LOGITS
     describe
    0.51
    ;(
    0.47
     ты
    0.46
    (
    0.46
    Describe
    0.46
     __(
    0.45
     um
    0.44
     flexible
    0.44
     اح
    0.43
     Describe
    0.43
    Activations Density 0.001%

    No Known Activations