© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 14685
    Prev
    Next
    INDEX
    Explanations

    drying and setting

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

    The neuron fires on mentions of drying or things drying (e.g. “dries,” “drying,” “dry,” “set” in the sense of drying), i.e. references to a drying/desiccation process.

    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
    𖥧
    -1.54
    надцать
    -1.45
    am
    -1.45
    Namun
    -1.38
    %);
    -1.32
    
    -1.31
    s
    -1.31
     conosci
    -1.30
    すぎて
    -1.30
    way
    -1.29
    POSITIVE LOGITS
    今天的
    1.52
     escuchado
    1.44
    我们的
    1.43
     Existing
    1.42
    通常
    1.42
     akzep
    1.41
    凤凰
    1.38
    łgorzata
    1.36
     unnoticed
    1.36
     wichtig
    1.34
    Activations Density 0.028%

    No Known Activations