© 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. 99490
    Prev
    Next
    INDEX
    Explanations

    free compound words

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

    The neuron is strongly activated by occurrences of the word “free.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     السياس
    -0.76
     WHEREAS
    -0.76
     concorso
    -0.72
    是指
    -0.71
    Recep
    -0.70
    Inherited
    -0.70
     gương
    -0.68
    評価
    -0.68
     acquisto
    -0.68
     erwor
    -0.65
    POSITIVE LOGITS
     free
    1.91
    form
    1.46
    free
    1.38
     Free
    1.31
    Free
    1.31
     form
    1.28
     FREE
    1.24
     freer
    1.21
    自由
    1.20
    FREE
    1.17
    Activations Density 0.027%

    No Known Activations