© 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. 22446
    Prev
    Next
    INDEX
    Explanations

    cobalt and compounds

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

    mentions of the element cobalt in chemical and scientific contexts.

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

    The neuron activates on mentions of the chemical element cobalt (including its symbol “Co”).

    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
    杙
    -3.20
    荜
    -2.69
     zelfs
    -2.52
    퐹
    -2.31
    锱
    -2.28
    茘
    -2.28
    伥
    -2.28
    躄
    -2.22
    AdvEx
    -2.16
    ꯸
    -2.16
    POSITIVE LOGITS
    6
    3.27
    5
    3.17
    8
    3.03
    Also
    2.98
    and
    2.89
    9
    2.88
    7
    2.64
    2
    2.61
    3
    2.53
    4
    2.47
    Activations Density 0.007%

    No Known Activations