© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48392
    Prev
    Next
    INDEX
    Explanations

    occurred, take, crash

    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
     paesi
    -0.96
     nodule
    -0.91
     województwie
    -0.90
    onner
    -0.84
     davvero
    -0.82
     मिला
    -0.79
     Paesi
    -0.78
    Puedes
    -0.78
    Congrats
    -0.77
    thritis
    -0.77
    POSITIVE LOGITS
     terrain
    0.97
    terrain
    0.94
     cellular
    0.92
    啉
    0.92
     sequence
    0.91
    當時
    0.90
     Jimenez
    0.89
     personnel
    0.89
    ﺎ
    0.89
     reportedly
    0.87
    Activations Density 0.022%

    No Known Activations