© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 28502
    Prev
    Next
    INDEX
    Explanations

    forum discussions and URLs

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

    This neuron detects forum interface and community site metadata text (e.g. “Forum,” “forums,” site‐branding tokens).

    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
     to
    -1.02
     than
    -1.01
    RTLE
    -0.98
     endwhile
    -0.93
     other
    -0.92
    uoš
    -0.91
     exciter
    -0.90
     garçons
    -0.88
    UELA
    -0.87
     of
    -0.87
    POSITIVE LOGITS
    <b>
    1.16
    ांकि
    1.03
    şil
    0.98
    şak
    0.96
     déposer
    0.90
    Membre
    0.88
     ouvrir
    0.88
    zą
    0.86
     liest
    0.86
     braços
    0.86
    Activations Density 0.016%

    No Known Activations