© 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. 13978
    Prev
    Next
    INDEX
    Explanations

    object/UI elements/variables followed by code/operators

    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
     mereka
    -1.00
    Törté
    -0.96
    ⓿
    -0.91
     réunions
    -0.91
    擔心
    -0.89
     sartén
    -0.88
     cuchara
    -0.87
     distritos
    -0.86
     inglesa
    -0.86
     faro
    -0.86
    POSITIVE LOGITS
     to
    0.95
    self
    0.94
    sel
    0.91
    letzt
    0.87
     sebel
    0.85
    jj
    0.84
    Jeff
    0.84
    Ed
    0.84
    seven
    0.83
     fréqu
    0.82
    Activations Density 0.014%

    No Known Activations