© 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. 33629
    Prev
    Next
    INDEX
    Explanations

    cat or kitty

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

    The main thing this neuron does is detect mentions of cats or cat‐related words.

    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
    </strong>
    -2.06
    </sup>
    -1.89
     a
    -1.84
    <em>
    -1.72
    </em>
    -1.60
    j
    -1.59
    tedrale
    -1.50
    (
    -1.50
    ”
    -1.44
    _
    -1.38
    POSITIVE LOGITS
    nip
    1.71
     who
    1.64
     There
    1.61
    ？？？
    1.59
    ụp
    1.57
    ˂
    1.52
    %;
    1.48
    nemu
    1.45
    ？？
    1.44
    >-->
    1.40
    Activations Density 0.047%

    No Known Activations