© 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. 119159
    Prev
    Next
    INDEX
    Explanations

    Filipino place names and terms starting with B

    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
    Ez
    -0.82
     curricular
    -0.78
     Architect
    -0.78
     Advocate
    -0.77
     cập
    -0.75
     Ez
    -0.75
     ἔ
    -0.74
    Literal
    -0.72
     ess
    -0.71
     estudi
    -0.71
    POSITIVE LOGITS
     gegebenen
    0.73
     individuellen
    0.72
     sari
    0.69
     gewöhn
    0.69
    MSM
    0.69
     Simult
    0.69
    قرأ
    0.68
     Possibility
    0.68
     Memor
    0.67
     granada
    0.66
    Activations Density 0.019%

    No Known Activations