© 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. 34-GEMMASCOPE-RES-131K
    7. 58805
    Prev
    Next
    INDEX
    Explanations

    ghosts

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

    The neuron strongly responds to the ‘|…|’ symbols and adjacent x/y coordinate variables, i.e. it flags absolute‐value expressions in math formulas.

    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
    ույ
    -0.82
     Wern
    -0.80
    VENTORY
    -0.79
     sociable
    -0.76
     ͜ʖ
    -0.75
    binom
    -0.74
    صلاح
    -0.73
     établie
    -0.73
     अध्य
    -0.73
     ügy
    -0.73
    POSITIVE LOGITS
     ghost
    0.91
     ghosts
    0.80
    Agents
    0.77
    噶
    0.75
     Oni
    0.75
     kla
    0.74
    orescent
    0.74
    xc
    0.74
     zer
    0.73
    ghost
    0.73
    Activations Density 0.000%

    No Known Activations