© 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. 22-GEMMASCOPE-RES-131K
    7. 66184
    Prev
    Next
    INDEX
    Explanations

    assurance and absence of worry

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

    The neuron detects words used in reassurance or confidence‐building phrases (e.g. “rest assured,” “absolute confidence,” “peace of mind,” “confident”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    haviours
    -1.29
    asable
    -0.92
    mentable
    -0.91
     but
    -0.90
    }+
    -0.86
    Ỉ
    -0.85
    nieren
    -0.84
    estacks
    -0.83
     rumput
    -0.82
    пами
    -0.82
    POSITIVE LOGITS
     worry
    2.16
     confident
    1.81
     worries
    1.67
     Worry
    1.65
    worry
    1.63
    confident
    1.56
     assurance
    1.50
    安心して
    1.47
     confidence
    1.46
     confidently
    1.43
    Activations Density 0.018%

    No Known Activations