© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15110
    Prev
    Next
    INDEX
    Explanations

    life, God, literature, cars, oil, cookies

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

    words and concepts related to abstract entities like ideas, topics, materials, or intellectual property.

    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
     utaf
    -1.08
     for
    -1.07
     there
    -1.04
     botines
    -1.03
    者が
    -1.02
     Proficiency
    -1.00
     nzuri
    -0.96
     kufanya
    -0.96
    沢山
    -0.94
    怎么做
    -0.93
    POSITIVE LOGITS
     during
    1.13
     its
    1.09
     continues
    1.06
     recent
    1.02
     is
    1.01
     will
    0.99
    一系列
    0.98
     was
    0.93
     continue
    0.93
    以及
    0.92
    Activations Density 0.080%

    No Known Activations