© 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. 70735
    Prev
    Next
    INDEX
    Explanations

    Al- compounds and altered

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

    words beginning with "Al" at the start of a line.

    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_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
    ſſen
    -2.88
    也很
    -2.66
    this
    -2.52
     também
    -2.34
    撼
    -2.25
    ῞
    -2.17
    ౮
    -2.17
    ܆
    -2.16
    쥰
    -2.14
    ?’
    -2.11
    POSITIVE LOGITS
     If
    2.89
     Your
    2.48
     Everything
    2.22
     It
    2.16
     What
    2.14
     упаковка
    2.11
    防火
    2.08
    珦
    2.05
     There
    2.05
     Many
    2.03
    Activations Density 0.001%

    No Known Activations