© 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. 10-GEMMASCOPE-RES-131K
    7. 104028
    Prev
    Next
    INDEX
    Explanations

    Sonic, Kirby, Hedgehog, Mega Man

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

    The neuron selectively fires on capitalized proper names and titles (i.e. proper nouns).

    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
    </
    -1.66
    ”
    -1.60
     הש
    -1.38
     unserem
    -1.38
     offer
    -1.33
     bieten
    -1.33
     offre
    -1.31
    .”
    -1.28
    im
    -1.25
     предлага
    -1.23
    POSITIVE LOGITS
     světa
    1.55
    melons
    1.48
    gegangen
    1.44
    闐
    1.41
     imprensa
    1.39
    涠
    1.34
     ontstaan
    1.33
    harapkan
    1.30
    ⢕
    1.27
    蚴
    1.26
    Activations Density 0.004%

    No Known Activations