© 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. 22-GEMMASCOPE-RES-131K
    7. 67040
    Prev
    Next
    INDEX
    Explanations

    list item separators

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

    This neuron picks out the author’s original post (the opening, topic‐setting sentences) rather than replies or comments.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     थे
    -1.20
     those
    -1.19
    образие
    -1.13
    ΤΟ
    -1.13
     many
    -1.13
    ଵ
    -1.08
    .”
    -1.08
    Тогда
    -1.07
     some
    -1.05
    orescent
    -1.05
    POSITIVE LOGITS
    recently
    1.05
     I
    1.05
     fonctionne
    1.00
     nulle
    0.99
     SIMILAR
    0.99
     haven
    0.98
     komplet
    0.97
     vorige
    0.94
     malen
    0.94
     is
    0.93
    Activations Density 0.025%

    No Known Activations