© 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. 34-GEMMASCOPE-RES-131K
    7. 49319
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers and 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_34/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
     costuras
    -1.05
    }
    -1.02
    ặn
    -1.02
    +"&
    -0.99
     Compos
    -0.99
    łka
    -0.97
    second
    -0.96
    秶
    -0.95
     kompati
    -0.95
     SECOND
    -0.95
    POSITIVE LOGITS
     of
    2.70
     August
    1.73
     April
    1.70
     September
    1.65
     December
    1.63
     June
    1.59
     July
    1.57
     November
    1.53
     October
    1.48
     January
    1.48
    Activations Density 0.009%

    No Known Activations