© 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. 22-GEMMASCOPE-RES-131K
    7. 14750
    Prev
    Next
    INDEX
    Explanations

    Smackdown, Type O Negative, Republic, Sloan Kettering

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

    This neuron activates for proper nouns, specifically names of organizations, brands, places, and entities.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     also
    -1.45
     in
    -1.40
     both
    -1.34
     Kości
    -1.28
     at
    -1.21
     from
    -1.09
     towar
    -1.09
     criatura
    -1.09
     praça
    -1.09
    を
    -1.06
    POSITIVE LOGITS
    必要がある
    1.32
    必要があります
    1.30
    ようになる
    1.16
     incontr
    1.12
     olika
    1.10
     enthou
    1.09
     aktualisiert
    1.05
    為に
    1.03
    RIP
    1.02
     mało
    1.02
    Activations Density 0.357%

    No Known Activations