© 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. 34-GEMMASCOPE-RES-131K
    7. 2990
    Prev
    Next
    INDEX
    Explanations

    cache and invalid arguments

    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_34/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
    <0xA7>
    -0.81
    叨
    -0.77
     forbindelse
    -0.74
    nyt
    -0.72
     pipette
    -0.71
    Ze
    -0.71
    lasts
    -0.71
     φι
    -0.71
    を送
    -0.70
    posables
    -0.70
    POSITIVE LOGITS
    IMDG
    1.02
     eviction
    0.90
     evicted
    0.84
    CACHE
    0.77
     Cache
    0.77
     Madura
    0.76
    Xa
    0.76
     Micron
    0.75
    ضع
    0.74
    getCache
    0.73
    Activations Density 0.021%

    No Known Activations