© 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. 87031
    Prev
    Next
    INDEX
    Explanations

    numbers with six digits

    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
    atron
    -0.93
    eraard
    -0.89
    "=
    -0.86
    -0.86
     stedet
    -0.86
     tibi
    -0.83
    Royal
    -0.82
    🌞
    -0.82
    Van
    -0.82
    Mar
    -0.82
    POSITIVE LOGITS
    BENEF
    0.88
    xymatrix
    0.87
    Vrij
    0.86
    DERE
    0.84
     quema
    0.83
    되지
    0.82
     vivere
    0.82
    还是要
    0.81
    Groet
    0.81
    CARACTER
    0.81
    Activations Density 0.162%
    No Known Activations