© 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. 19601
    Prev
    Next
    INDEX
    Explanations

    to [audience]

    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
    ↵
    -1.38
    erweise
    -1.17
    ționale
    -1.15
     had
    -1.14
    tierra
    -1.11
     along
    -1.10
    静静
    -1.10
     інших
    -1.10
     unieke
    -1.09
    自体は
    -1.09
    POSITIVE LOGITS
    :
    1.41
    踯
    1.40
    ändert
    1.31
    輊
    1.30
    こちら
    1.26
     those
    1.23
     when
    1.23
     こちら
    1.21
    those
    1.20
    而言
    1.20
    Activations Density 0.067%

    No Known Activations