© 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. 1601
    Prev
    Next
    INDEX
    Explanations

    which regulate or control

    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
     telah
    -1.11
    leave
    -1.02
    leaving
    -0.98
    lemon
    -0.97
     voelt
    -0.95
    edonia
    -0.93
    implies
    -0.92
    éndolo
    -0.92
     Meets
    -0.92
     мають
    -0.91
    POSITIVE LOGITS
     is
    1.99
     controls
    1.91
     responsible
    1.77
     help
    1.65
     helps
    1.63
     control
    1.59
     controlling
    1.55
     serve
    1.52
     sør
    1.51
     enable
    1.43
    Activations Density 0.250%

    No Known Activations