© 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. 117371
    Prev
    Next
    INDEX
    Explanations

    keywords after colons

    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
    itum
    -0.86
     confining
    -0.84
     restraining
    -0.81
    Ή
    -0.78
    yped
    -0.77
     infinitive
    -0.77
     confines
    -0.77
     capa
    -0.77
     wana
    -0.77
     foreseen
    -0.75
    POSITIVE LOGITS
     threw
    0.81
    pakah
    0.75
    лосо
    0.74
     caufe
    0.74
     these
    0.71
     Dichter
    0.71
    Tasty
    0.71
     insertion
    0.70
     heraus
    0.69
     走
    0.68
    Activations Density 0.007%

    No Known Activations