© 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. 64753
    Prev
    Next
    INDEX
    Explanations

    Jonah and the whale

    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
     Bré
    -0.80
    moor
    -0.77
     batal
    -0.75
     LIMITATIONS
    -0.75
     produttore
    -0.74
    ữu
    -0.73
    rafts
    -0.69
    واق
    -0.69
    дой
    -0.68
     noisy
    -0.67
    POSITIVE LOGITS
     Jonah
    2.09
    Jonah
    1.71
     swallowed
    1.11
     Jonas
    0.96
     whale
    0.94
     sign
    0.90
     swallowing
    0.84
     Whale
    0.82
    Jonas
    0.82
     JON
    0.82
    Activations Density 0.006%

    No Known Activations