© 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. 1092
    Prev
    Next
    INDEX
    Explanations

    cervical spine and neck

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

    anatomical terms related to vertebrae and spinal structures, particularly cervical vertebrae like C1, C2, and C3.

    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
     ankles
    -0.98
     waistband
    -0.93
     tibia
    -0.93
     thigh
    -0.91
    knee
    -0.91
     Abdominal
    -0.89
     pelvis
    -0.86
     tibial
    -0.85
     groin
    -0.85
     knee
    -0.84
    POSITIVE LOGITS
     cervical
    2.39
     neck
    2.23
     Neck
    1.96
    cerv
    1.91
    Neck
    1.83
     Cervical
    1.76
    neck
    1.69
    Cerv
    1.62
     cerv
    1.28
     necks
    1.26
    Activations Density 0.067%

    No Known Activations