© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32087
    Prev
    Next
    INDEX
    Explanations

    question or attachment identifier

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

    The neuron flags very common function words (high‐frequency tokens like “our,” “public,” “sealed,” “will,” “any,” 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_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
    ditos
    -0.81
    เอก
    -0.72
    初中
    -0.71
    cmu
    -0.71
     ended
    -0.70
     đó
    -0.69
    オーストラリア
    -0.69
     democrática
    -0.68
     hoped
    -0.67
    égories
    -0.67
    POSITIVE LOGITS
     FUND
    1.04
     samtidigt
    0.88
     getters
    0.85
     доступа
    0.84
    IBU
    0.83
     plantar
    0.82
     GENE
    0.82
    éndolo
    0.82
     DIRECT
    0.81
    ^^^^^^^^
    0.81
    Activations Density 0.000%

    No Known Activations