© 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. 116362
    Prev
    Next
    INDEX
    Explanations

    nano-composites or nano-structures

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

    prefixes like "nano" and "micro" related to scientific measurements and scales.

    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
    kin
    -1.09
    wski
    -1.05
    polis
    -0.96
    men
    -0.93
    por
    -0.91
    pre
    -0.90
    sergio
    -0.90
    ser
    -0.89
    ked
    -0.88
    plated
    -0.88
    POSITIVE LOGITS
     echar
    0.91
    Beginning
    0.88
    loads
    0.85
     réfrigérateur
    0.83
     reef
    0.80
    lauch
    0.80
    zyms
    0.79
    peek
    0.79
    mpeg
    0.78
     éto
    0.76
    Activations Density 0.113%

    No Known Activations