© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 64309
    Prev
    Next
    INDEX
    Explanations

    names of months

    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
    Negative Logits
     its
    -1.37
     their
    -1.18
     our
    -1.13
    。　　
    -1.08
     chrétiens
    -1.07
     recientes
    -1.00
     liberté
    -0.98
    itename
    -0.98
    
    -0.96
     experiencias
    -0.94
    POSITIVE LOGITS
    fordshire
    1.20
    llten
    1.10
    際には
    1.00
    自行车
    1.00
     concub
    0.99
     entrambi
    0.98
    payers
    0.98
    CIUDAD
    0.98
    urization
    0.96
     tenses
    0.96
    Activations Density 0.008%

    No Known Activations