© 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. 65980
    Prev
    Next
    INDEX
    Explanations

    scientific citations and references

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

    publication reference numbers, especially page ranges with hyphens in academic citations.

    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
     beneath
    -0.98
     specifico
    -0.89
     With
    -0.88
     during
    -0.85
    盆
    -0.83
    готови
    -0.82
     untuk
    -0.81
    らは
    -0.78
    现有
    -0.77
     with
    -0.76
    POSITIVE LOGITS
    遡
    1.06
    わない
    0.96
    processed
    0.94
    匮
    0.94
     الأك
    0.93
     dominante
    0.93
    returning
    0.93
     ergonom
    0.89
     principalement
    0.87
     autobio
    0.87
    Activations Density 0.001%

    No Known Activations