© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15610
    Prev
    Next
    INDEX
    Explanations

    calculus, derivative, and gradient

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èr
    -1.02
    為に
    -0.97
     緑
    -0.93
    ից
    -0.93
    is
    -0.89
    みよう
    -0.86
     すぐ
    -0.85
    ITY
    -0.84
    INDA
    -0.84
     repeated
    -0.84
    POSITIVE LOGITS
     Krzyż
    0.89
    イヤレス
    0.89
    子さん
    0.88
     CreateTagHelper
    0.87
     }).
    0.85
     חיצוני
    0.85
     karyawan
    0.85
    uginosa
    0.84
     around
    0.84
    完美
    0.84
    Activations Density 0.012%

    No Known Activations