© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70909
    Prev
    Next
    INDEX
    Explanations

    old state or identifier

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

    The neuron activates on occurrences of the token “old,” as used in variable or identifier names.

    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
    ">
    -1.70
    赓
    -1.66
     make
    -1.63
    <bos>
    -1.63
     analis
    -1.63
     ask
    -1.59
    殒
    -1.55
     can
    -1.53
     facilitates
    -1.51
    blurRadius
    -1.50
    POSITIVE LOGITS
    経緯
    1.95
     exceedingly
    1.95
    m
    1.94
     decidedly
    1.90
    www
    1.90
     overly
    1.86
    na
    1.86
    ow
    1.84
    perhaps
    1.84
    actually
    1.79
    Activations Density 0.009%

    No Known Activations