© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2275
    Prev
    Next
    INDEX
    Explanations

    food items and dishes

    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
    ようです
    -1.02
     italianos
    -0.98
     decorativos
    -0.98
     the
    -0.97
     decorativas
    -0.92
     foo
    -0.91
     cristianos
    -0.88
     Gewalt
    -0.85
    ansha
    -0.83
    o
    -0.82
    POSITIVE LOGITS
     with
    1.55
     served
    1.20
    бурге
    1.05
     recipe
    1.00
    iration
    0.97
    ímos
    0.96
    agrams
    0.96
    lighed
    0.94
    Filmographie
    0.94
    Legenda
    0.91
    Activations Density 0.033%

    No Known Activations