© 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. 34-GEMMASCOPE-RES-131K
    7. 102591
    Prev
    Next
    INDEX
    Explanations

    in the context of

    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
     something
    -1.38
     same
    -1.27
     anything
    -1.23
    Something
    -1.20
     чего
    -1.13
    何か
    -1.12
    onos
    -1.09
     everything
    -1.06
    一切
    -1.05
     qualcosa
    -1.02
    POSITIVE LOGITS
     regarding
    1.59
     this
    1.44
     these
    1.40
     regards
    1.38
     besides
    1.14
     each
    1.13
     poszczegól
    1.12
     regard
    1.04
     môžete
    1.03
     concerning
    1.02
    Activations Density 0.062%

    No Known Activations