© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 129087
    Prev
    Next
    INDEX
    Explanations

    Olivia, Isaac, elderly, Full, This, It, Last, strict

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

    The neuron is specialized to pick up standalone decimal numbers (e.g. floating‐point scores).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    了许多
    -1.62
    ↵↵
    -1.52
     Però
    -1.49
     réglementation
    -1.47
    了不少
    -1.41
    Ausstattung
    -1.37
    l
    -1.36
     таких
    -1.34
     jedoch
    -1.32
     però
    -1.30
    POSITIVE LOGITS
     "..\..\
    1.57
    bof
    1.52
     ezek
    1.52
     '/':
    1.47
    enance
    1.44
    </tfoot>
    1.41
    tling
    1.40
    yled
    1.38
     that
    1.38
    ized
    1.36
    Activations Density 0.035%

    No Known Activations