© 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. 156128
    Prev
    Next
    INDEX
    Explanations

    onyx, peace, address, banks, uncommon

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

    contrasting or negative aspects

    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
    𝒖
    0.44
     因为
    0.43
     Stair
    0.43
    వాత
    0.42
     ActivityCompat
    0.41
     Expect
    0.41
    䏍
    0.40
    𝒅
    0.40
    𝒙
    0.40
     LoginPage
    0.40
    POSITIVE LOGITS
    トレンド
    0.51
    ジェル
    0.46
    オリジナル
    0.46
    ベルト
    0.46
     jist
    0.45
     limo
    0.45
     fad
    0.44
    ласти
    0.44
     vermel
    0.44
     sprou
    0.43
    Activations Density 0.001%

    No Known Activations