© 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. 10-GEMMASCOPE-RES-131K
    7. 61227
    Prev
    Next
    INDEX
    Explanations

    Hallelujah

    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_10/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
    b
    -2.80
     These
    -2.42
    f
    -2.20
     diesen
    -2.11
     berätt
    -2.02
    轱
    -1.99
    i
    -1.95
    èrement
    -1.91
    zembro
    -1.91
    ANSION
    -1.91
    POSITIVE LOGITS
    We
    2.23
    ных
    2.08
     semblent
    1.85
    ङ
    1.70
     montrent
    1.69
     コート
    1.68
    癭
    1.66
    轳
    1.66
     insbesondere
    1.66
     filhos
    1.64
    Activations Density 0.006%

    No Known Activations