© 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. 10-GEMMASCOPE-RES-131K
    7. 9180
    Prev
    Next
    INDEX
    Explanations

    HOLD, HOLDER, HOLDINGS

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

    The neuron fires on any occurrence of the substring “hold” (in various words like hold, holders, holdings, 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_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
    .
    -3.89
    ’
    -3.05
    v
    -2.98
    }
    -2.67
    ᱹ
    -2.41
     His
    -2.39
     Other
    -2.31
     According
    -2.30
    >
    -2.23
    をも
    -2.22
    POSITIVE LOGITS
    
    3.11
    撄
    2.95
    </strong>
    2.81
    灕
    2.72
    ⸂
    2.70
    他们是
    2.69
    懨
    2.67
    ).
    2.59
    薀
    2.58
    𖤣
    2.56
    Activations Density 0.013%

    No Known Activations