© 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. 109596
    Prev
    Next
    INDEX
    Explanations

    bibliographic citations

    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
     because
    -1.82
     at
    -1.76
     while
    -1.71
     in
    -1.70
     not
    -1.70
     with
    -1.66
     on
    -1.65
     through
    -1.55
     from
    -1.54
     eight
    -1.53
    POSITIVE LOGITS
     Dinas
    1.54
     evtl
    1.53
     diversos
    1.48
    mainly
    1.44
     gigantic
    1.41
     soooo
    1.40
    蓠
    1.38
     sooo
    1.37
     différents
    1.36
     crea
    1.34
    Activations Density 0.008%

    No Known Activations