© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62584
    Prev
    Next
    INDEX
    Explanations

    mission statement

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

    This neuron detects section headings and key terms related to an organization’s mission and strategic planning (e.g. “mission,” “purpose,” “strategic plan,” “goals,” “outcome”).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    DetailView
    -0.88
    pues
    -0.87
     мужская
    -0.84
    λε
    -0.82
     polega
    -0.82
     khoe
    -0.82
     главное
    -0.81
     каком
    -0.81
    Gir
    -0.79
    thalle
    -0.79
    POSITIVE LOGITS
     statement
    4.69
     statements
    3.52
    statement
    3.50
     Statement
    3.25
    Statement
    3.02
     STATEMENT
    2.83
    statements
    2.64
    STATEMENT
    2.63
     Statements
    2.53
    Statements
    2.42
    Activations Density 0.049%

    No Known Activations