© 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. 11963
    Prev
    Next
    INDEX
    Explanations

    starts of sentences or code

    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
    🏺
    -0.89
    делать
    -0.80
     relevant
    -0.79
     actin
    -0.76
    opho
    -0.75
     铜
    -0.73
     провин
    -0.73
     fragments
    -0.72
    minyak
    -0.72
    órmula
    -0.71
    POSITIVE LOGITS
    HomeAsUp
    0.79
     forfeited
    0.77
    artament
    0.75
     Upland
    0.73
     challeng
    0.73
    ValueType
    0.73
    ülés
    0.72
    Alcal
    0.71
     valu
    0.70
    仲間
    0.70
    Activations Density 0.004%

    No Known Activations