© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106884
    Prev
    Next
    INDEX
    Explanations

    code separators and specific nouns

    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
     Yields
    -0.91
    GDP
    -0.83
     yields
    -0.79
    ∅
    -0.77
    wym
    -0.75
     Natal
    -0.75
     parang
    -0.75
     yield
    -0.74
     Glad
    -0.73
     foro
    -0.72
    POSITIVE LOGITS
    César
    0.80
    äger
    0.78
     nhất
    0.78
    ienie
    0.77
    ///////////////
    0.73
    ᱯ
    0.73
    CONCLUS
    0.72
    をつ
    0.71
    ляются
    0.71
    but
    0.71
    Activations Density 0.001%

    No Known Activations