© 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. 10-GEMMASCOPE-RES-131K
    7. 14025
    Prev
    Next
    INDEX
    Explanations

    copyright notices

    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_10/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
    )
    -2.02
    }
    -1.88
     моей
    -1.64
     Templo
    -1.59
    :
    -1.57
    mathrm
    -1.52
    .”
    -1.52
    そうです
    -1.50
    してしまった
    -1.49
    そうだ
    -1.48
    POSITIVE LOGITS
     semblent
    1.63
    معرفی
    1.55
     découver
    1.47
    ଃ
    1.39
     aident
    1.38
     mostrarán
    1.37
     familières
    1.36
     devenue
    1.34
    dée
    1.32
     bocetos
    1.31
    Activations Density 0.001%

    No Known Activations