© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12473
    Prev
    Next
    INDEX
    Explanations

    numerical and date formats

    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
     who
    -1.10
     and
    -1.02
     which
    -0.97
     gestorben
    -0.92
     berbagai
    -0.91
    laient
    -0.88
     it
    -0.88
    不一样
    -0.88
     create
    -0.86
     vieron
    -0.86
    POSITIVE LOGITS
     ananas
    1.14
     âges
    1.08
     cushions
    1.08
     héro
    1.02
     pneus
    1.01
     siècles
    1.01
     vanille
    1.01
     paie
    0.99
     poupée
    0.99
     definit
    0.97
    Activations Density 0.001%

    No Known Activations