© 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. 67722
    Prev
    Next
    INDEX
    Explanations

    cheer and cheerfulness

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

    The neuron activates on the root “cheer,” firing for any occurrence or derivative (cheer, cheered, cheering, cheerleading, Cheerios, etc.).

    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
     enchanting
    -3.06
    開設
    -2.89
     }
    -2.78
     enjoyable
    -2.72
    ']
    -2.72
     inherently
    -2.69
    ୈ
    -2.64
     Each
    -2.58
    ৢ
    -2.58
     eagerly
    -2.53
    POSITIVE LOGITS
    </i>
    3.48
    0
    3.06
    .
    3.06
    {
    2.69
    7
    2.66
    that
    2.58
    是
    2.55
    8
    2.45
     sio
    2.39
    selben
    2.31
    Activations Density 0.004%

    No Known Activations