© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 93936
    Prev
    Next
    INDEX
    Explanations

    friendly, cuddly, intelligent, calm, affectionate

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

    The neuron fires on longer, specialized technical nouns—especially multi-syllable animal or disease terms.

    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
    dienste
    -0.87
    әһ
    -0.86
    chos
    -0.84
     refreshment
    -0.84
    íu
    -0.83
    才能
    -0.81
     сма
    -0.79
    letes
    -0.79
     zmienia
    -0.78
     çeşit
    -0.77
    POSITIVE LOGITS
     affectionate
    1.35
     calm
    1.34
     friendly
    1.34
     intelligent
    1.32
     intelligence
    1.28
     gentle
    1.18
     loving
    1.16
     loyal
    1.12
     easy
    1.05
     trusting
    1.05
    Activations Density 0.015%

    No Known Activations