© 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. 73023
    Prev
    Next
    INDEX
    Explanations

    `this.props` and `self.`

    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
    smaller
    -0.99
    Seznam
    -0.96
    ATEUR
    -0.96
    そうですが
    -0.95
     parlamento
    -0.95
    最近は
    -0.94
    Lịch
    -0.93
    FUENTES
    -0.90
    Каждый
    -0.89
    してしまう
    -0.89
    POSITIVE LOGITS
    /***
    1.07
    bemos
    0.99
    ந
    0.99
     chúng
    0.97
     zwi
    0.96
    ｒ
    0.96
     &
    0.93
    很好
    0.93
    달
    0.93
     tutaj
    0.92
    Activations Density 0.003%

    No Known Activations