© 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. 90504
    Prev
    Next
    INDEX
    Explanations

    specific language

    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
    戚
    -0.69
    frontmatter
    -0.69
    〉
    -0.69
    gether
    -0.69
     FAQ
    -0.66
     prey
    -0.66
    segue
    -0.66
     RecyclerView
    -0.66
     الانت
    -0.65
     Boud
    -0.65
    POSITIVE LOGITS
    reathe
    0.76
     Bia
    0.71
    INGO
    0.68
    彼女は
    0.67
     kể
    0.65
     Sre
    0.65
     crock
    0.64
     ನಿ
    0.64
    纠结
    0.64
     trừ
    0.62
    Activations Density 0.073%

    No Known Activations