© 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. 9137
    Prev
    Next
    INDEX
    Explanations

    action of

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

    The neuron selectively responds to the noun “action,” spotting instances of that exact word in various contexts.

    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
     recoger
    -1.55
     herausgegeben
    -1.49
     nostro
    -1.48
     '/';
    -1.46
     Γ
    -1.45
     boletín
    -1.45
    €/
    -1.45
     einschließlich
    -1.45
     version
    -1.43
    ,’
    -1.41
    POSITIVE LOGITS
     crouching
    1.58
    必然
    1.57
     kwamba
    1.52
     öv
    1.49
     fussy
    1.46
    
    1.46
    他也
    1.45
    してしまった
    1.45
     educate
    1.43
    裃
    1.43
    Activations Density 0.043%

    No Known Activations