© 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. 34-GEMMASCOPE-RES-131K
    7. 1258
    Prev
    Next
    INDEX
    Explanations

    CX, CCL, citation, code, species

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

    chemical and protein notations with "CX" prefixes such as CXCR and CXCL.

    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
     Encounter
    -0.78
    encounter
    -0.73
     cambios
    -0.73
     encounter
    -0.73
    accumulation
    -0.72
    acją
    -0.71
    muito
    -0.70
    Cambio
    -0.69
     Emil
    -0.69
    скі
    -0.69
    POSITIVE LOGITS
     Honourable
    0.72
     בל
    0.69
    รี
    0.67
    ်
    0.66
     Kevin
    0.65
     Benef
    0.65
    Sal
    0.64
    Si
    0.64
    熟
    0.61
    wnętr
    0.61
    Activations Density 0.071%

    No Known Activations