© 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. 77151
    Prev
    Next
    INDEX
    Explanations

    speech and language therapy

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

    The neuron is highly sensitive to mentions of therapeutic or medical support services (e.g., speech, language, therapy, medical care).

    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
     ValueError
    -0.88
     PREG
    -0.85
     Veterin
    -0.84
    iblichen
    -0.84
     laiko
    -0.84
     CLIMATE
    -0.82
    Meno
    -0.82
     sapiens
    -0.82
     CHEMISTRY
    -0.81
     welk
    -0.80
    POSITIVE LOGITS
     speech
    2.47
     therapy
    2.19
     therapies
    2.14
     Speech
    2.14
    speech
    2.06
    Speech
    2.03
     therapists
    1.96
     therapist
    1.73
    peech
    1.56
     therapeutic
    1.54
    Activations Density 0.042%

    No Known Activations