© 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. 77239
    Prev
    Next
    INDEX
    Explanations

    get back

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

    The neuron fires on first‐person plural future‐tense service promises—especially phrases like “we will get back to you” (or “we’ll be in touch,” 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
     forcibly
    -0.76
    ोटो
    -0.72
     khỏi
    -0.69
    ToServer
    -0.69
    หว่าง
    -0.69
    อร
    -0.68
    RequestDto
    -0.68
    賑
    -0.67
    リラックス
    -0.67
    varez
    -0.66
    POSITIVE LOGITS
     back
    1.82
     get
    1.34
     terug
    1.30
     respond
    1.30
     åter
    1.23
     getting
    1.16
     vissza
    1.16
    回
    1.14
    กลับ
    1.14
     responds
    1.13
    Activations Density 0.018%

    No Known Activations