© 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. 34-GEMMASCOPE-RES-131K
    7. 45544
    Prev
    Next
    INDEX
    Explanations

    preparing cross-linked, hollow, monoclonal

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

    scholarly or scientific text that introduces a research finding or describes properties of materials.

    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_34/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
    logical
    -1.07
    更
    -1.06
    virtual
    -1.06
    牴
    -1.05
    tifiable
    -1.05
     zrobić
    -1.04
    normal
    -1.00
     wtedy
    -0.98
    itisation
    -0.98
    ancial
    -0.98
    POSITIVE LOGITS
     высоко
    1.17
     високо
    1.05
    çs
    1.02
    jangan
    1.00
    niet
    0.97
     utf
    0.96
     bakteri
    0.95
     ergonom
    0.95
     prêtre
    0.95
     portugu
    0.93
    Activations Density 0.818%

    No Known Activations