© 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. 112807
    Prev
    Next
    INDEX
    Explanations

    making polite requests

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

    The neuron activates on instances of the word “please,” i.e. polite request markers.

    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
     If
    -1.88
    semitism
    -1.86
     denies
    -1.85
     heinous
    -1.80
    中秋
    -1.78
    賡
    -1.78
    郸
    -1.77
     they
    -1.77
     when
    -1.75
    </em>
    -1.74
    POSITIVE LOGITS
    }
    2.27
    鵟
    1.91
    {
    1.90
    もの
    1.73
    zed
    1.71
    му
    1.69
    ments
    1.69
     lesquelles
    1.68
    );
    1.63
    ures
    1.61
    Activations Density 0.007%

    No Known Activations