© 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. 34-GEMMASCOPE-RES-131K
    7. 3124
    Prev
    Next
    INDEX
    Explanations

    medical treatment or body parts

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

    programming code files, particularly focusing on syntax elements like imports, declarations, and namespaces.

    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_34/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
     Glä
    -0.83
     durability
    -0.76
     DUR
    -0.69
    Robbie
    -0.69
     TEXT
    -0.68
    ี่ยว
    -0.68
    zug
    -0.67
    gens
    -0.67
    Durability
    -0.66
    रा
    -0.65
    POSITIVE LOGITS
    клада
    0.69
     Maxwell
    0.69
     Ramsey
    0.69
     поча
    0.69
    ῖ
    0.66
    サス
    0.65
     Sachen
    0.64
     Swin
    0.64
     affirm
    0.64
     副
    0.64
    Activations Density 0.042%

    No Known Activations