© 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. 95626
    Prev
    Next
    INDEX
    Explanations

    gene accession number

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

    formatted table structures with rows and columns.

    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
     corriger
    -1.23
    hese
    -1.21
    cisive
    -1.20
     applau
    -1.18
    instru
    -1.18
    behaved
    -1.16
     图库
    -1.16
     bapt
    -1.15
    chose
    -1.13
    joined
    -1.12
    POSITIVE LOGITS
     espirituales
    1.32
     their
    1.22
    ↵↵
    1.18
     \\
    1.15
     usually
    1.14
     millones
    1.14
     being
    1.12
     what
    1.11
     \
    1.10
    “
    1.10
    Activations Density 0.004%

    No Known Activations