© 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. 65622
    Prev
    Next
    INDEX
    Explanations

    end of code blocks

    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
     we
    -2.75
    䊉
    -2.30
    ”
    -2.17
    it
    -2.13
    樒
    -2.09
    )
    -2.08
    </strong>
    -2.08
     her
    -1.99
     diseñ
    -1.99
     recientemente
    -1.95
    POSITIVE LOGITS
    摭
    2.75
    arbonato
    2.38
    л
    2.30
    .《
    2.25
    遄
    2.23
    ﾝ
    2.20
    肫
    2.20
    縯
    2.17
    namentales
    2.16
    𓄹
    2.14
    Activations Density 0.002%

    No Known Activations