© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 71498
    Prev
    Next
    INDEX
    Explanations

    titration, neutralization, hydroxide

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

    chemical titration and neutralization terms in scientific contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron strongly activates on terminology associated with chemical titration and quantitative analytical procedures.

    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
     Fungsi
    -1.08
     vientre
    -1.07
     hän
    -1.02
    鈞
    -1.01
    혹
    -1.01
    dass
    -0.96
     ὁ
    -0.96
    illées
    -0.95
    larınız
    -0.95
     stoff
    -0.94
    POSITIVE LOGITS
    mény
    1.13
    meleon
    1.11
     quickly
    1.09
    UTRAL
    1.05
     pinta
    1.05
     сторону
    1.05
    清
    1.02
    "]
    
    1.02
     supplied
    1.01
    arm
    1.00
    Activations Density 0.044%

    No Known Activations