© 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. 22-GEMMASCOPE-RES-131K
    4. 39657
    Prev
    Next
    INDEX
    Explanations

    HIV, selected entry inhibitors, subtypes

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

    scientific and technical content in academic papers, particularly related to measurements, concentrations, and experimental data.

    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
     flotte
    -1.38
     horloge
    -1.27
     vanille
    -1.20
    Asociación
    -1.19
     eisen
    -1.19
     eis
    -1.16
     parfum
    -1.14
    茈
    -1.14
     enorme
    -1.13
    menschen
    -1.13
    POSITIVE LOGITS
     from
    1.65
     Each
    1.52
     each
    1.48
     with
    1.45
     after
    1.41
     for
    1.30
     at
    1.30
     teniendo
    1.24
     second
    1.23
     left
    1.23
    Activations Density 0.142%

    No Known Activations