© 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. 10-GEMMASCOPE-RES-131K
    7. 112258
    Prev
    Next
    INDEX
    Explanations

    gummy bears

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

    The neuron fires on words containing the letter sequence “ummi” (as in “gummy,” “gummi,” or “dummies”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    si
    -2.45
     This
    -2.41
    
    -2.38
    ᥬ
    -2.03
    ꪔ
    -2.02
    }$
    -1.98
    敉
    -1.96
     intelligent
    -1.92
     desenli
    -1.91
     viaja
    -1.88
    POSITIVE LOGITS
    ↵↵
    2.55
    
    2.06
     faſt
    1.99
    O
    1.88
     wich
    1.85
     vicino
    1.84
    because
    1.83
     سایر
    1.80
     будет
    1.78
     растения
    1.78
    Activations Density 0.001%

    No Known Activations