© 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. 89791
    Prev
    Next
    INDEX
    Explanations

    Cat Power, Management of, Q:

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron primarily activates on tokens containing digits (i.e. numeric literals, version numbers, or counts).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    }));
    -0.82
    aysia
    -0.79
    tcb
    -0.78
    偏差
    -0.77
    escola
    -0.76
     Schools
    -0.76
    !!!
    -0.75
     عزیز
    -0.75
    !!!!
    -0.75
    !!!!!
    -0.74
    POSITIVE LOGITS
     potencia
    0.82
    抿
    0.79
     父
    0.79
     Kapoor
    0.77
    自分が
    0.76
    users
    0.74
    ómica
    0.73
     mortos
    0.71
    learn
    0.71
    ств
    0.69
    Activations Density 0.001%

    No Known Activations