© 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. 68297
    Prev
    Next
    INDEX
    Explanations

    Mn and manganese

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

    The neuron activates for the chemical element manganese (Mn) and its abbreviation in scientific and chemical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    渽
    -2.84
    歘
    -2.67
    但
    -2.67
    涐
    -2.66
     But
    -2.64
    
    -2.63
    ꯸
    -2.55
    麈
    -2.50
     lakini
    -2.44
    mvh
    -2.41
    POSITIVE LOGITS
    from
    2.73
    and
    2.70
     '
    2.66
    遢
    2.58
    which
    2.58
     мире
    2.47
     schlagen
    2.45
     =
    2.44
    –
    2.38
     "
    2.30
    Activations Density 0.004%

    No Known Activations