© 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. 108002
    Prev
    Next
    INDEX
    Explanations

    proper names and labels

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

    The neuron is detecting single-quote tokens (the apostrophe used as a string delimiter).

    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
    的白
    -0.75
    rile
    -0.74
     tres
    -0.74
    ".
    -0.73
    gul
    -0.71
     niños
    -0.71
    限
    -0.69
     sabah
    -0.68
    @^
    -0.68
     Paso
    -0.67
    POSITIVE LOGITS
     sür
    0.91
     skills
    0.89
     bandwagon
    0.86
    skills
    0.82
    riculares
    0.82
     Linkedin
    0.79
    tionen
    0.79
     education
    0.78
    غي
    0.78
     指輪
    0.78
    Activations Density 0.000%

    No Known Activations