© 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. 73593
    Prev
    Next
    INDEX
    Explanations

    medical and technical terms

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

    quotation marks and enclosed text in formal documents or legal language.

    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_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
     miljö
    -1.19
    -1.16
     område
    -1.15
    sprzed
    -1.13
    vertre
    -1.03
     geene
    -1.02
     filós
    -1.00
    بره
    -1.00
    ÍA
    -0.98
     varier
    -0.98
    POSITIVE LOGITS
     or
    1.22
     "
    1.18
     this
    1.16
     will
    1.04
    </em>
    1.04
     the
    1.03
     '
    1.03
     или
    1.02
    i
    1.02
    NewReader
    1.00
    Activations Density 0.001%

    No Known Activations