© 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. 49102
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by descriptions

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

    The neuron strongly activates on numeric tokens (numbers).

    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
     princí
    -0.95
     silueta
    -0.92
     ול
    -0.89
    romeda
    -0.86
    ائج
    -0.85
    alanta
    -0.84
    的情况
    -0.84
    年来
    -0.82
     compañ
    -0.82
     colleague
    -0.82
    POSITIVE LOGITS
     quest
    1.63
     entirety
    1.61
     dealings
    1.46
     attempt
    1.38
     attempts
    1.26
     travels
    1.20
     infancy
    1.18
     heyday
    1.18
     guise
    1.17
     capacity
    1.14
    Activations Density 0.036%

    No Known Activations