© 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. 227663
    Prev
    Next
    INDEX
    Explanations

    specific adjective-noun pairs

    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
    1
    0.50
    v
    0.48
    正規
    0.48
    drive
    0.47
    press
    0.46
    k
    0.46
    inträ
    0.46
    nä
    0.46
    巡
    0.46
    lag
    0.45
    POSITIVE LOGITS
    चारियों
    0.45
     konusu
    0.45
     Oreo
    0.44
     만들어
    0.44
     годом
    0.43
    伖
    0.42
     propylene
    0.42
     ادی
    0.41
    くなり
    0.41
     Addresses
    0.41
    Activations Density 0.001%

    No Known Activations