© 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. 15351
    Prev
    Next
    INDEX
    Explanations

    syndrome referred to

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

    legal and academic document formatting patterns such as headers, section markers, and citation notations.

    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
     some
    -1.19
     Some
    -1.13
     If
    -1.11
    1
    -1.08
     or
    -1.04
    8
    -1.02
    Alguns
    -1.02
     in
    -1.00
     jeśli
    -1.00
     inneces
    -0.99
    POSITIVE LOGITS
     trimestre
    1.09
     ruine
    1.06
    🖐
    1.03
     chô
    1.02
     MÁ
    1.02
    憷
    0.99
    ≦
    0.99
    蟶
    0.98
    🪔
    0.98
     lavabo
    0.98
    Activations Density 0.013%

    No Known Activations