© 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. 10-GEMMASCOPE-RES-131K
    7. 90818
    Prev
    Next
    INDEX
    Explanations

    names after punctuation

    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_10/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
     bienfaits
    -1.64
    曖昧さ
    -1.49
     begrenzt
    -1.45
     ところ
    -1.41
     оригі
    -1.41
    少しずつ
    -1.38
    ambiance
    -1.34
    𝒦
    -1.34
    Hadi
    -1.34
    最後に
    -1.34
    POSITIVE LOGITS
     there
    2.14
     because
    2.02
     who
    1.84
     especially
    1.80
     and
    1.78
     by
    1.70
     even
    1.66
     this
    1.64
     here
    1.64
     often
    1.48
    Activations Density 0.336%

    No Known Activations