© 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. 34-GEMMASCOPE-RES-131K
    7. 57704
    Prev
    Next
    INDEX
    Explanations

    pixel and dip units

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

    The neuron fires on numeric tokens—especially CSS length values (digits used in “px” measurements).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     quelques
    -0.99
    Demikian
    -0.98
     early
    -0.97
     odstran
    -0.97
    Beberapa
    -0.95
    ◍
    -0.95
     yağı
    -0.94
    politician
    -0.94
    priest
    -0.93
     many
    -0.93
    POSITIVE LOGITS
    ين
    0.86
    før
    0.84
    ag
    0.81
     では
    0.81
    renda
    0.79
     microbes
    0.79
    ｅ
    0.79
     ἀ
    0.78
    咤
    0.78
     вещь
    0.77
    Activations Density 0.011%

    No Known Activations