© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101378
    Prev
    Next
    INDEX
    Explanations

    forgetting or remembering

    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_10/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
     more
    -1.91
     When
    -1.71
     Here
    -1.59
     tantas
    -1.55
     então
    -1.52
    ebenarnya
    -1.52
     many
    -1.45
    してた
    -1.41
    怎樣
    -1.40
    มากกว่า
    -1.39
    POSITIVE LOGITS
    in
    1.76
     of
    1.75
    usually
    1.62
     ridic
    1.59
    ou
    1.55
    即使
    1.52
    2
    1.48
    now
    1.41
     Minggu
    1.41
    currently
    1.41
    Activations Density 0.005%

    No Known Activations