© 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. 104759
    Prev
    Next
    INDEX
    Explanations

    safety programs, pathway, leishmaniasis, theater, five kids, governments, fish, brands, microorganisms, tract, stress

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

    technical or scientific terms related to biology, medicine, or specialized fields.

    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
     to
    -1.37
     along
    -1.20
     or
    -0.95
     instead
    -0.94
     same
    -0.93
     together
    -0.92
     there
    -0.90
     impact
    -0.90
     separately
    -0.89
     while
    -0.86
    POSITIVE LOGITS
     who
    1.64
     geworden
    1.14
     számára
    1.09
     quien
    1.06
    谁
    1.05
    ḧ
    1.04
    kter
    1.01
    who
    1.00
     hosszú
    0.99
     nonché
    0.99
    Activations Density 0.242%

    No Known Activations