© 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. 93562
    Prev
    Next
    INDEX
    Explanations

    express or implied

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

    The neuron strongly activates on forward‐slash tokens used in file paths (e.g. the “/” in directory or URL paths).

    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
    after
    -0.72
     after
    -0.70
     Crusaders
    -0.68
     strongly
    -0.67
    加盟
    -0.66
     not
    -0.62
     より
    -0.62
    vial
    -0.62
     both
    -0.59
    oci
    -0.59
    POSITIVE LOGITS
     regionale
    0.77
    IKA
    0.76
    ventilation
    0.75
     saga
    0.74
    штей
    0.72
     اقتصاد
    0.71
    ))=
    0.71
     região
    0.70
     DECLARATION
    0.69
    pica
    0.67
    Activations Density 0.055%

    No Known Activations