© 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. 76684
    Prev
    Next
    INDEX
    Explanations

    that introduces clauses

    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
     and
    -1.93
     hombros
    -1.47
     agujeros
    -1.30
     kwietnia
    -1.24
    licet
    -1.21
    鮡
    -1.20
     czerwca
    -1.19
    quête
    -1.16
     omtrent
    -1.13
     miljoen
    -1.11
    POSITIVE LOGITS
     there
    2.69
     says
    2.14
     if
    2.08
     suggests
    1.97
     this
    1.76
     could
    1.74
     should
    1.72
     would
    1.70
     suggest
    1.68
     seemed
    1.66
    Activations Density 0.036%

    No Known Activations