© 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. 4269
    Prev
    Next
    INDEX
    Explanations

    words starting with "Mel"

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

    The neuron strongly fires on tokens containing the substring “mel” (e.g. words or names beginning with “Mel”).

    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
     geringe
    -0.84
    allinen
    -0.78
     предела
    -0.77
     Others
    -0.77
    ре
    -0.77
     answers
    -0.75
     Antworten
    -0.74
     يعد
    -0.73
     monetary
    -0.73
     they
    -0.73
    POSITIVE LOGITS
     MEL
    1.10
    Mel
    1.02
     メル
    1.00
     mayhem
    0.98
     Mel
    0.97
     Mayhem
    0.93
    calfe
    0.90
    paddingTop
    0.90
     melting
    0.89
     Madness
    0.88
    Activations Density 0.024%

    No Known Activations