© 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. 84400
    Prev
    Next
    INDEX
    Explanations

    sponge bob characters and bikini

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

    The neuron fires most strongly on structural or “header‐style” tokens—i.e. section titles, all‐caps headings or other stand‐alone labels in a document.

    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
    Anthropo
    -0.80
     cui
    -0.79
     enga
    -0.77
    infix
    -0.76
    lightweight
    -0.76
     Akan
    -0.76
     agentes
    -0.75
     consolidating
    -0.73
     तु
    -0.73
     Drucker
    -0.73
    POSITIVE LOGITS
     SpongeBob
    1.81
     Squid
    1.44
    gebob
    1.43
    Sponge
    1.30
     Bikini
    1.25
     Spon
    1.23
     Sponge
    1.23
     Square
    1.16
     spon
    1.15
    Squid
    1.12
    Activations Density 0.004%

    No Known Activations