© 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. 10-GEMMASCOPE-RES-131K
    7. 103862
    Prev
    Next
    INDEX
    Explanations

    iterator, automata, algorithms, visitor, writer

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

    the word "ator" as a suffix in programming-related terms like "iterator", "Enumerator", and "Comparator".

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    Another
    -1.39
     даже
    -1.36
     やすい
    -1.34
    3
    -1.31
    ↵
    -1.30
     иногда
    -1.29
     mengel
    -1.27
     politischen
    -1.26
     câteva
    -1.24
    2
    -1.24
    POSITIVE LOGITS
     tives
    1.45
    鼕
    1.42
     cursus
    1.40
     recomendable
    1.39
    ᥬ
    1.38
     revenu
    1.38
    onucleotides
    1.37
    forKey
    1.34
    CURLOPT
    1.34
    ౭
    1.34
    Activations Density 0.026%

    No Known Activations