© 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. 65165
    Prev
    Next
    INDEX
    Explanations

    map Point, Pakistan detained

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

    The neuron fires strongly on the names of software libraries, SDKs, APIs, classes, and other technical identifiers.

    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
     Google
    -1.80
     google
    -1.55
    Google
    -1.47
    GoogleMap
    -1.25
    google
    -1.24
     GOOGLE
    -1.00
    GOOGLE
    -0.98
    谷歌
    -0.89
     Marker
    -0.85
     Ян
    -0.76
    POSITIVE LOGITS
    װ
    0.84
    Succ
    0.81
     corridor
    0.78
     priv
    0.76
    FRC
    0.73
     کار
    0.73
     सद
    0.73
    NameExpr
    0.72
    ルフ
    0.72
     pog
    0.72
    Activations Density 0.010%

    No Known Activations