© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107124
    Prev
    Next
    INDEX
    Explanations

    blocking things

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

    The neuron reliably fires on words naming cars or other vehicles (especially in contexts of parking or blocking).

    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
    ätta
    -0.74
     به
    -0.73
     drowned
    -0.73
    ücksich
    -0.73
     ausgeschlossen
    -0.71
    tablissements
    -0.71
    ӧ
    -0.70
     escaping
    -0.69
    Ground
    -0.69
    Seq
    -0.68
    POSITIVE LOGITS
     blocking
    3.45
    blocking
    2.91
    Blocking
    2.88
     Blocking
    2.88
     blockade
    2.33
     blockage
    2.27
     bloque
    2.08
     obstructing
    2.08
     blocked
    2.08
     block
    2.06
    Activations Density 0.029%

    No Known Activations