© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130222
    Prev
    Next
    INDEX
    Explanations

    Hydrogen Bond

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

    technical or scientific content, particularly focusing on specialized terminology in engineering, automotive, and chemistry domains.

    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
     الأطفال
    -1.27
    ถ้า
    -1.23
    )]:
    -1.20
     domingos
    -1.18
    ENCIÓN
    -1.17
     подрост
    -1.16
    详细信息
    -1.15
    ۓ
    -1.15
    ajte
    -1.10
    -1.09
    POSITIVE LOGITS
     difp
    1.63
     fubject
    1.54
     caufe
    1.52
     fufficient
    1.52
     neceff
    1.46
     testing
    1.44
     pleaf
    1.43
     reafon
    1.41
     sorento
    1.41
     test
    1.39
    Activations Density 0.014%

    No Known Activations