© 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. 10-GEMMASCOPE-RES-131K
    7. 73273
    Prev
    Next
    INDEX
    Explanations

    discussion of instability

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

    The neuron activates specifically on occurrences of the noun “instability.”

    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
    When
    -3.63
    However
    -3.42
    Since
    -3.39
    Once
    -3.36
    There
    -3.36
    If
    -3.36
    With
    -3.28
    Within
    -3.28
    It
    -3.27
    Initially
    -3.27
    POSITIVE LOGITS
    ');
    3.03
    ⟞
    2.95
    はその
    2.92
    暻
    2.88
    
    2.84
    すすめ
    2.73
    ⟝
    2.73
    忖
    2.72
    垢
    2.72
    是这样的
    2.72
    Activations Density 0.016%

    No Known Activations