© 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. 117415
    Prev
    Next
    INDEX
    Explanations

    first numbered items

    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
     other
    -2.25
     this
    -1.87
     additional
    -1.78
     that
    -1.69
     after
    -1.61
     many
    -1.48
     even
    -1.47
     more
    -1.46
     until
    -1.41
     some
    -1.38
    POSITIVE LOGITS
    ⓵
    1.37
     commencer
    1.30
    首先
    1.25
     сначала
    1.23
     ridiculously
    1.23
     pierws
    1.21
     améli
    1.20
    ➀
    1.18
     ۱
    1.17
     เล
    1.17
    Activations Density 0.023%

    No Known Activations