© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16003
    Prev
    Next
    INDEX
    Explanations

    "Show HN" project titles

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

    The neuron fires on emphatic or “excited” emphasis markers—especially exclamation points (and the surrounding capitalized, high-energy tokens) indicating strong emphasis or excitement.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    🤑
    -1.16
    🫶
    -1.11
    %%%%%%%%%%%%%%%%
    -1.09
    🐾
    -1.08
     members
    -1.04
     key
    -1.01
                          
    -0.99
    }
    -0.98
                                   
    -0.98
     rijk
    -0.97
    POSITIVE LOGITS
    蕁
    1.15
     rempliss
    1.09
     magnifiques
    1.09
     épu
    1.06
     déchir
    1.05
     preparo
    1.05
     étrang
    1.05
     tatuagens
    1.05
     crochê
    1.03
     chronicles
    1.03
    Activations Density 0.008%

    No Known Activations