© 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. 45513
    Prev
    Next
    INDEX
    Explanations

    stable and unstable states

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

    This neuron detects occurrences of the word “stable” (e.g. in terms like “Stable Isotope,” “stable product,” etc.).

    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
     acredita
    -1.06
    
    -1.05
     thwarted
    -1.04
    撄
    -1.02
     activer
    -1.02
    为什么会
    -1.01
    
    -1.00
    乄
    -1.00
    yyv
    -1.00
    茑
    -0.99
    POSITIVE LOGITS
     stable
    1.88
     stability
    1.82
     Stable
    1.81
    稳定
    1.76
     Stability
    1.70
     stabili
    1.62
    stable
    1.59
     Stab
    1.59
     unstable
    1.59
    Stable
    1.57
    Activations Density 0.028%

    No Known Activations