© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 15926
    Prev
    Next
    INDEX
    Explanations

    cache use

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     I
    1.05
    the
    1.04
    ные
    0.86
    nya
    0.81
    taining
    0.81
    ่า
    0.80
    tk
    0.79
    sembles
    0.78
     transversal
    0.78
    (
    0.78
    POSITIVE LOGITS
    ৬
    1.30
    در
    1.23
    ية
    1.20
     caches
    1.20
    ด
    1.12
    د
    1.10
    മ
    1.09
    缓存
    1.07
     Cache
    1.05
    д
    1.03
    Activations Density 0.024%

    No Known Activations