© 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. 22-GEMMASCOPE-RES-131K
    7. 33673
    Prev
    Next
    INDEX
    Explanations

    opinion or regular

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

    The neuron lights up on words that frame or signal a request or question—e.g. “ask,” “asking,” “questions,” “for,” “avoid”—i.e. phrasing that explicitly poses or refers to asking for something.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     hű
    -0.83
    centroids
    -0.79
    fdata
    -0.79
     крайней
    -0.75
    geladen
    -0.75
     відповід
    -0.75
    $$$
    -0.74
    няются
    -0.74
     RI
    -0.74
     säs
    -0.74
    POSITIVE LOGITS
     merely
    1.84
     simply
    1.67
     simplemente
    1.55
     mere
    1.49
     просто
    1.43
    Mere
    1.20
     simplesmente
    1.16
     semplicemente
    1.11
     purely
    1.05
     general
    1.02
    Activations Density 0.052%

    No Known Activations