© 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. 130210
    Prev
    Next
    INDEX
    Explanations

    numbers, roman numerals, and codes

    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
     before
    -1.38
     this
    -1.31
    S
    -1.27
     one
    -1.26
     This
    -1.24
     Before
    -1.20
     put
    -1.20
    O
    -1.19
    A
    -1.18
    C
    -1.18
    POSITIVE LOGITS
     elektrik
    1.52
     telefonu
    1.45
     echa
    1.41
    ⛦
    1.41
     onOptions
    1.40
    熜
    1.38
    骉
    1.38
    égorie
    1.38
     sezonu
    1.33
    ppings
    1.32
    Activations Density 0.007%

    No Known Activations