© 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. 10-GEMMASCOPE-RES-131K
    7. 70329
    Prev
    Next
    INDEX
    Explanations

    uniqueness and extermination

    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
    2
    -3.48
    0
    -2.77
     möjligt
    -2.58
     mögliche
    -2.48
     availa
    -2.47
     When
    -2.47
    Regarding
    -2.42
    ન
    -2.42
     italiens
    -2.42
     ähnliche
    -2.36
    POSITIVE LOGITS
    蛩
    2.53
     “
    2.44
     –
    2.36
     (“
    2.28
    ῎
    2.20
    さんに
    2.19
    d
    2.19
    {
    2.16
    韬
    2.14
     утро
    2.13
    Activations Density 0.005%

    No Known Activations