© 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. 68068
    Prev
    Next
    INDEX
    Explanations

    Carbon nanotubes

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

    numerical identifiers or code values in structured data or tables.

    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
    ｿ
    -1.18
    szt
    -1.11
     coloridas
    -1.09
     Tér
    -1.08
     colch
    -1.08
     brancas
    -1.05
     considère
    -1.04
    擧
    -1.04
    tiap
    -1.03
     ако
    -1.02
    POSITIVE LOGITS
    um
    1.23
    om
    1.15
    peed
    1.13
    u
    1.08
    ance
    1.08
     ?>>
    1.06
    sion
    1.05
    up
    1.02
    first
    1.00
    ering
    0.99
    Activations Density 0.004%

    No Known Activations