© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 7183
    Prev
    Next
    INDEX
    Explanations

    ground up, bottom up

    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
    bsc
    -0.76
    𝒍
    -0.68
    Vag
    -0.67
     Ayala
    -0.66
    downloads
    -0.65
    らなかった
    -0.64
     progesterone
    -0.63
    malle
    -0.63
     Loo
    -0.62
    rededor
    -0.62
    POSITIVE LOGITS
     up
    2.02
    Up
    1.91
    up
    1.84
    UP
    1.78
     Up
    1.73
     UP
    1.69
    アップ
    1.18
    upa
    1.08
    ขึ้น
    1.07
    ups
    1.04
    Activations Density 0.040%

    No Known Activations