© 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. 173104
    Prev
    Next
    INDEX
    Explanations

    legal, administrative, or technical context

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

    historical and age debate

    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
     london
    0.48
     bowl
    0.46
    定的
    0.46
    把
    0.45
     broiler
    0.44
     •
    0.44
     ◆
    0.43
    ả
    0.42
    யில
    0.42
     把
    0.42
    POSITIVE LOGITS
    Zy
    0.52
    downloads
    0.51
    visualization
    0.49
    Tare
    0.48
    rules
    0.47
    ZH
    0.47
    HIP
    0.46
    Licenses
    0.46
    ამო
    0.44
    GREEN
    0.44
    Activations Density 0.000%

    No Known Activations