© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63564
    Prev
    Next
    INDEX
    Explanations

    TF IDF PMI

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

    This neuron fires on tokens that look like technical identifiers or versioned/code names (e.g. “t-SNE,” “tf.js,” numeric version strings).

    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
    Lenny
    -0.78
    펠
    -0.75
    _{-
    -0.73
    ヨン
    -0.72
    yaw
    -0.72
     Scotsman
    -0.72
    爱你
    -0.70
     ウール
    -0.70
    retch
    -0.69
     REVOL
    -0.69
    POSITIVE LOGITS
    idf
    1.18
    IDF
    1.13
     IDF
    1.09
     TF
    1.09
    TF
    1.02
     tf
    0.94
    tf
    0.90
     Term
    0.89
    Term
    0.86
    PMI
    0.84
    Activations Density 0.020%

    No Known Activations