© 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. 22-GEMMASCOPE-RES-131K
    7. 129563
    Prev
    Next
    INDEX
    Explanations

    parent id, manager id, ref id

    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_22/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
     모든
    -1.09
    ἃ
    -1.08
    inį
    -0.96
    ⼥
    -0.94
    directors
    -0.94
     การ์ตูน
    -0.93
     Simplemente
    -0.92
    FACTORY
    -0.91
    paroles
    -0.90
    阄
    -0.90
    POSITIVE LOGITS
     that
    1.09
     if
    1.08
     this
    0.99
     none
    0.97
     other
    0.94
     you
    0.93
     like
    0.91
    これに
    0.88
    和其他
    0.88
    other
    0.88
    Activations Density 0.013%

    No Known Activations