© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 93869
    Prev
    Next
    INDEX
    Explanations

    Africa needs, in vitro

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

    numeric sequences in IDs, particularly in URLs, XML tags, and digital content.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     need
    -1.84
     needed
    -1.34
    需要
    -1.30
     needs
    -1.27
    Need
    -1.18
     more
    -1.14
     necessity
    -1.07
    need
    -1.04
     like
    -1.02
     such
    -1.02
    POSITIVE LOGITS
    énergie
    1.02
    Espace
    0.98
     véritables
    0.98
    Recherche
    0.97
    Cia
    0.97
     énon
    0.95
    Taille
    0.94
     précédemment
    0.94
    Utilisation
    0.93
    诅
    0.93
    Activations Density 0.002%

    No Known Activations