© 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. 10-GEMMASCOPE-RES-131K
    7. 131020
    Prev
    Next
    INDEX
    Explanations

    planetary radius

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

    The neuron detects occurrences of the word “planet” (including variants like “planets,” “planetary,” and “exoplanet”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     صفحۀ
    -2.55
    
    -2.52
    灕
    -2.50
    𞤢
    -2.48
    átiles
    -2.38
     flurry
    -2.28
    ཫ
    -2.23
     laiss
    -2.23
    куртка
    -2.22
    Adverten
    -2.19
    POSITIVE LOGITS
    {
    2.84
    E
    2.69
    )
    2.52
    O
    2.42
    So
    2.39
     The
    2.31
    man
    2.27
    ]
    2.27
    <b>
    2.27
    le
    2.17
    Activations Density 0.006%

    No Known Activations