© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68536
    Prev
    Next
    INDEX
    Explanations

    enough or insufficient

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

    This neuron lights up on words that convey quantitative measures or magnitudes (e.g., distances, depths, amounts, resolution, time, dynamic range).

    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
    Each
    -1.24
     chacune
    -1.09
    每
    -0.91
    Removed
    -0.91
    あなた
    -0.90
    昨日の
    -0.90
    showed
    -0.89
    İyi
    -0.89
    今月
    -0.88
    本当は
    -0.88
    POSITIVE LOGITS
     enough
    1.82
     sufficient
    1.68
     suficiente
    1.58
     to
    1.41
     required
    1.34
     insufficient
    1.25
    所需
    1.22
     suficientes
    1.21
     sufficiently
    1.21
     unless
    1.19
    Activations Density 0.063%

    No Known Activations