© 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. 49260
    Prev
    Next
    INDEX
    Explanations

    country names, dimensions, company names

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

    The neuron activates on instances of Android-style dimension units—specifically the “dp” and “sp” unit suffixes in layout measurements.

    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
     extraordinarily
    -0.85
     Lage
    -0.84
     excellent
    -0.82
    вные
    -0.82
     So
    -0.81
     very
    -0.78
    слен
    -0.78
    PageModule
    -0.78
    づけ
    -0.77
     seemingly
    -0.77
    POSITIVE LOGITS
    Quali
    1.01
     eſt
    0.97
    ՚
    0.96
     экрана
    0.93
     unidad
    0.89
     $_{\
    0.88
     prêtre
    0.87
    become
    0.86
     ポケット
    0.86
    }$.
    0.85
    Activations Density 0.000%

    No Known Activations