© 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. 10-GEMMASCOPE-RES-131K
    7. 119875
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation in code or lists

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

    years in the 1950s, particularly "195" followed by a digit.

    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
     Scritto
    -1.52
     of
    -1.52
     hatta
    -1.48
     if
    -1.47
    fiques
    -1.44
    tismo
    -1.43
     gruppen
    -1.38
    INTRODUCCIÓN
    -1.36
    erobic
    -1.34
    Тарих
    -1.33
    POSITIVE LOGITS
     território
    1.70
    莅
    1.55
     equilíbrio
    1.53
     pescoço
    1.47
     already
    1.45
     schreibt
    1.45
     princípio
    1.43
     eixo
    1.43
     relógio
    1.41
     comprimidos
    1.41
    Activations Density 0.148%

    No Known Activations