© 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. 1476
    Prev
    Next
    INDEX
    Explanations

    copyright and licensing

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

    The neuron fires on any token containing one or more “=” characters—e.g. standalone equals signs or multi‐character operators like “==”, “+=”, “-=”, 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
    тельно
    -0.73
    =:
    -0.72
     pres
    -0.72
    얕
    -0.72
     Yam
    -0.71
     well
    -0.71
    ָא
    -0.71
    髦
    -0.70
    yPos
    -0.70
     .:
    -0.70
    POSITIVE LOGITS
    untos
    0.93
    ąd
    0.83
     apparence
    0.82
    ズル
    0.81
    鸢
    0.81
    甗
    0.79
     adorned
    0.79
    zogen
    0.79
    త్ర
    0.77
    一开始
    0.77
    Activations Density 0.038%

    No Known Activations