© 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. 49829
    Prev
    Next
    INDEX
    Explanations

    speech and its applications

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

    The neuron fires strongly on the token “speech” (including in compounds like “speechless,” “speech recognition,” etc.).

    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
    豊富
    -0.92
    ﾛ
    -0.91
     exped
    -0.84
    ﾆ
    -0.84
    可以看到
    -0.83
    曲を
    -0.83
    psies
    -0.82
     встречи
    -0.82
     kří
    -0.81
    シャツ
    -0.80
    POSITIVE LOGITS
    ifying
    1.34
     pathologist
    1.16
    bubble
    1.07
     acts
    1.02
     Speech
    1.02
    speech
    0.98
     impediment
    0.97
     actúa
    0.97
    writer
    0.94
     bubble
    0.93
    Activations Density 0.011%

    No Known Activations