© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 102622
    Prev
    Next
    INDEX
    Explanations

    cellular channels

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

    technical terminology in patents or academic papers about wireless communication systems.

    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
    県立
    -0.82
    AMG
    -0.75
     Phil
    -0.75
     LTE
    -0.75
    Phil
    -0.74
    ᶻ
    -0.74
     kontakta
    -0.73
     Wi
    -0.72
    Литература
    -0.70
     alat
    -0.69
    POSITIVE LOGITS
     burst
    0.84
    speech
    0.82
     kênh
    0.81
     speech
    0.80
     Viter
    0.79
     channels
    0.78
     DATOS
    0.78
    ẏ
    0.74
     Denim
    0.74
     Burst
    0.73
    Activations Density 0.058%

    No Known Activations