© 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. 34-GEMMASCOPE-RES-131K
    7. 60315
    Prev
    Next
    INDEX
    Explanations

    `init Iron`, `Rap son`, `Cypress Park`, `Inter leukin`, `Q :`

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

    special characters and symbols in technical or programming contexts.

    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
     because
    -1.00
     several
    -0.89
     its
    -0.88
     begins
    -0.88
     began
    -0.87
    AnimationsModule
    -0.86
    †
    -0.82
     behavior
    -0.82
    вест
    -0.81
    ־
    -0.81
    POSITIVE LOGITS
    still
    0.96
     pè
    0.90
    Ljava
    0.88
     diriger
    0.86
     Homemade
    0.85
     spil
    0.85
     hypotension
    0.84
    篷
    0.84
    variance
    0.82
    ἂ
    0.82
    Activations Density 0.000%

    No Known Activations