© 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. 99028
    Prev
    Next
    INDEX
    Explanations

    nano, micro, hemi, meta, mac prefixes

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

    This neuron activates on occurrences of the substring “nan,” i.e. words using the “nano-” prefix (like nanowires, nanostructures, nanocellulose, 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
     all
    -1.01
     Richard
    -0.97
     with
    -0.94
     taking
    -0.91
     Some
    -0.88
     Completely
    -0.88
     new
    -0.87
    約束
    -0.87
     these
    -0.85
     including
    -0.85
    POSITIVE LOGITS
    glicher
    1.05
     verrou
    1.02
     verticale
    1.02
    🪦
    1.01
    kelig
    0.99
     enthou
    0.99
     whimsical
    0.99
     vernac
    0.98
    designed
    0.98
    ATRE
    0.97
    Activations Density 0.238%

    No Known Activations