© 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. 25711
    Prev
    Next
    INDEX
    Explanations

    interest in something

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

    The main thing this neuron does is detect mentions of interest or curiosity (e.g., “interest,” “interested,” “interesting,” “curiosity”).

    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
    er
    -2.59
     facendo
    -2.53
    莇
    -2.47
    </b>
    -2.39
    u
    -2.36
    揠
    -2.28
    In
    -2.27
    至於
    -2.20
    asanjo
    -2.11
     ガラス
    -2.09
    POSITIVE LOGITS
    .
    2.67
    籐
    2.48
    نگار
    2.45
    </h3>
    2.39
     voor
    2.25
    
    2.22
    اته
    2.16
    d
    2.13
    巿
    2.09
    ⢅
    2.08
    Activations Density 0.019%

    No Known Activations