© 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. 22-GEMMASCOPE-RES-131K
    7. 34527
    Prev
    Next
    INDEX
    Explanations

    one to another

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

    The neuron fires on directional transition phrases that link one item to another—particularly “from … to …” constructions.

    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
     uniquement
    -1.05
    cembre
    -0.97
     rajut
    -0.96
     Dij
    -0.95
    бав
    -0.94
     '#
    -0.94
     только
    -0.93
    摸了
    -0.92
     pouze
    -0.91
    ducteur
    -0.90
    POSITIVE LOGITS
     another
    2.39
     others
    2.31
     other
    1.27
    另一个
    1.24
    อีก
    1.19
    Another
    1.16
    Others
    1.15
     otro
    1.12
    others
    1.12
     другое
    1.09
    Activations Density 0.041%

    No Known Activations