© 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. 32040
    Prev
    Next
    INDEX
    Explanations

    blogger.com/profile/

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

    This neuron responds to blogger.com URLs—especially the numeric post/profile paths in those links.

    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
     Seat
    -0.85
    irac
    -0.85
     Oculus
    -0.82
     died
    -0.79
    ('|
    -0.75
    loria
    -0.74
     Tull
    -0.72
     Till
    -0.72
    isEqualTo
    -0.71
    Quantification
    -0.71
    POSITIVE LOGITS
    blogspot
    1.37
     Blogger
    1.30
    Blogger
    1.19
    blogger
    1.09
     blogger
    1.09
     blog
    0.98
     Blog
    0.96
    Blog
    0.96
     gadgets
    0.93
     bloggers
    0.82
    Activations Density 0.045%

    No Known Activations