© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77516
    Prev
    Next
    INDEX
    Explanations

    iconography and code structure

    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
    的吗
    -0.99
    丹药
    -0.90
     powiedzieć
    -0.80
    ؐ
    -0.80
     intends
    -0.77
     willst
    -0.76
    trg
    -0.75
    ミュ
    -0.75
     λογ
    -0.75
    の方は
    -0.75
    POSITIVE LOGITS
    Rounded
    1.01
    rounded
    0.85
    👮
    0.82
    ांक
    0.78
    cón
    0.77
    voke
    0.76
    lagten
    0.75
    Icon
    0.75
     jeszcze
    0.74
     وضع
    0.74
    Activations Density 0.010%

    No Known Activations