© 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. 81104
    Prev
    Next
    INDEX
    Explanations

    important contributions, through collaborations, rights arising

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

    technology, robotics, news, learning

    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
    waffe
    0.48
    劊
    0.47
    na
    0.46
     Schwarzenegger
    0.45
    mien
    0.44
    istico
    0.44
    வா
    0.44
     poser
    0.44
    avam
    0.42
    <0x8B>
    0.41
    POSITIVE LOGITS
     robberies
    0.46
    ρ
    0.45
     paroles
    0.45
     médias
    0.44
     únicas
    0.44
     automóviles
    0.44
    τη
    0.43
    ತ್ಯ
    0.43
     otomatis
    0.43
     ações
    0.43
    Activations Density 0.001%

    No Known Activations