© 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. 34-GEMMASCOPE-RES-131K
    7. 78269
    Prev
    Next
    INDEX
    Explanations

    native followed by a noun

    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_34/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
    艄
    -0.89
    Alfredo
    -0.88
     Infra
    -0.85
    Epit
    -0.85
     règle
    -0.83
     naszym
    -0.81
    ון
    -0.81
    ampli
    -0.81
    artis
    -0.79
    无力
    -0.79
    POSITIVE LOGITS
    QUIR
    1.10
     born
    1.01
    tomie
    0.99
    posia
    0.97
    ่อย
    0.95
    fier
    0.93
    entric
    0.93
     certainly
    0.91
    前方
    0.91
    窖
    0.89
    Activations Density 0.015%

    No Known Activations