© 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. 224627
    Prev
    Next
    INDEX
    Explanations

    look at

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

    technical terms and roles

    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
    汝
    0.48
    clude
    0.43
    ERC
    0.43
    服用
    0.43
    希
    0.43
    蜷
    0.42
     बोस
    0.42
    erde
    0.41
    咗
    0.41
    千
    0.41
    POSITIVE LOGITS
     advancements
    0.55
     introducir
    0.52
     geliştir
    0.52
     साज
    0.50
     विका
    0.48
     exploring
    0.48
     สร้าง
    0.47
     поднима
    0.47
     symbolism
    0.46
     進
    0.46
    Activations Density 0.000%

    No Known Activations