© 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. 32934
    Prev
    Next
    INDEX
    Explanations

    software licenses and code packages

    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
    utica
    -0.84
    uestamente
    -0.82
    mbre
    -0.69
     ジュ
    -0.68
    mbra
    -0.68
    EqualTo
    -0.66
    Dream
    -0.66
     Freedom
    -0.66
    ю
    -0.65
    夜
    -0.65
    POSITIVE LOGITS
    ండి
    0.80
     stag
    0.68
    になり
    0.68
     Absicht
    0.67
     ście
    0.67
    ストア
    0.66
    veaux
    0.66
     maw
    0.64
    richTextPanel
    0.63
    レシピ
    0.63
    Activations Density 0.076%

    No Known Activations